Machine Learning Engineer jobs in Israel

The road algorithm team is responsible for the critical and challenging task of detecting the drivable lanes on the road. We focus on Deep Learning algorithms, classical Computer Vision and Geometric Modeling algorithms. We are looking for an Algorithm Developer to help us advance our technology and push the boundaries of what's possible in autonomous driving. What will your job look like: • Research and develop state-of-the-art computer vision and deep learning algorithms for ADAS and autonomous driving. • Participate in the entire development cycle, from initial research and prototyping to deployment on real-time embedded systems within the vehicle. • Collaborate with engineering and research teams in Computer Vision, Machine Learning, and Data Engineering to solve real-life problems. • Analyze large datasets to improve algorithm performance and robustness. All you need is: • B.Sc. or M.Sc. in Computer Science or Engineering, with excellent academic performance. • 4+ years of hands-on experience developing deep learning algorithms, preferably in computer vision or perception for autonomous driving systems. • Solid understanding of data structures, algorithms, and deep learning principles. • Hands-on experience in algorithm development. • Strong problem-solving skills and the ability to work independently and as part of a team. Nice to have: • Experience with TensorFlow or PyTorch. • Familiarity with cloud platforms and tools (e.g., AWS, GCP). Mobileye changes the way we drive, from preventing accidents to semi and fully autonomous vehicles. If you are an excellent, bright, hands-on person with a passion to make a difference come to lead the revolution!

Mobileye is the world leader in automotive and driving assistance systems, developing the world's most advanced software technologies and hardware architectures. Our team in Haifa develops cutting-edge technologies to deploy deep learning and computer vision algorithms efficiently on the Mobileye platform. Our work contributes to saving lives and advancing the capabilities of autonomous vehicles. Check out our technology in action: https://www.youtube.com/watch?v=50NPqEla0CQ We are looking for a deep learning software engineer to join the Mobileye Autonomous Driving software group in Haifa, focusing on Deep Learning optimizations. This role offers an exciting opportunity to collaborate with highly talented engineers, contribute to an innovative product, and work with cutting-edge AI technologies. What will your job look like: • Develop a software product that optimizes deep learning networks. The optimizations include learnable techniques such as quantization, pruning and compression. This software product is the initial stage of the deep learning inference flow and is essential for enabling Mobileye’s deep learning networks to operate efficiently on low-power hardware within vehicles. • Development is mostly in Python programming language, using deep learning frameworks such as Pytorch. • Collaborate closely with Mobileye’s algorithm teams to ensure the fast and accurate deployment of their state-of-the-art models. • The work encompasses the entire software development cycle, including code implementation, unit testing, CI/CD processes, and more. • Literature research and POC implementation of new optimization algorithms. • Your work will position you at the forefront of machine learning optimizations. All you need is: • BSc/MSc in Computer Science/ Electrical Engineering with computer science chain. • 5+ years experience in Neural Networks/Deep Learning. • Hands-on experience with PyTorch and deep learning frameworks. • Strong Python programming skills and experience developing production-grade software. • Knowledge of C/C++ and experience with containerized environments – an advantage. • Experience in CI/CD pipelines and containerized environments.

Mobileye’s Hawkeye team is developing advanced close-range 3D perception for autonomous vehicles, enabling safe automated parking and low-speed maneuvers in tight environments. We build multi-camera deep learning systems for precise and reliable understanding of the vehicle’s surroundings. What will your job look like: • Research and develop cutting-edge end-to-end 3D perception models combining geometry and semantics. • Work on 3D Semantic Occupancy, Geometry Reasoning, 3D Reconstruction, 3D Object Detection, and related tasks. • Innovate in multi-view fusion, motion handling, and spatial representation learning. • Deliver models that run on real vehicles and integrate into production systems. All you need is: • 4+ years of hands-on experience in Machine Learning and Deep Learning. • M.Sc. in a relevant field (Machine Learning / Computer Vision / Robotics / similar). • B.Sc. from a leading university. • Strong Python development skills. • Highly motivated, hard-working, proactive, and driven to solve challenging problems. • Ability to operate in a fast-paced research & development environment. Nice to have: • PhD or relevant academic publications. • Experience with Linux, Git, Docker, C++. • Knowledge in 3D perception, computer vision, or robotics. • Industry experience working on CV and Deep Learning. Mobileye changes the way we drive, from preventing accidents to semi and fully autonomous vehicles. If you are an excellent, bright, hands-on person with a passion to make a difference come to lead the revolution!

Mobileye is a global leader in autonomous vehicle (AV) technology. If you’re an experienced deep learning developer driven by a passion to shape the future of mobility, join us to make AV a reality. The 3D Perception team builds transformer-based vision models trained on large-scale driving video for the next generation of autonomous vehicles. Our end-to-end temporal network fuses multi-view cameras into a unified 3D sensing state that powers planning. What will your job look like? • Develop, implement and optimize state-of-the-art transformer-based temporal vision models. • Extend network capabilities, analyze results and errors, and deliver measurable improvements to the driving scene understanding. • Work shoulder-to-shoulder in a large, collaborative group. • Research and integrate the latest advancements in 3d detection and perception. • Improve algorithmic performance through rigorous experimentation and innovation. • Work with large-scale datasets. • Research new advances in the field from the literature and industry. • Code primarily in Python. All you need is: • M.Sc. in Computer Science or a related field. • 3+ years of experience developing, implementing, training and analyzing deep learning algorithms in Python. • Top-tier mathematical, analytical, and coding skills. • Strong self-learner and research capabilities with a proven track record from industry or academia. Nice to have: • PhD in Computer Science or a related discipline. • Experience in computer vision, multi-view geometry and 3D reconstruction.

You will be part of Mobileye's REM (Road Experience Management) department which is responsible for the automatic High Definition map-making process, which is a key technology in Mobileye's autonomous driving and high-end Driving Assistance systems. You will be joining the team that builds the state-of-the-art AI-powered relevancy systems at scale. You will be designing and implementing semantic understanding engines that power data-driven products across autonomous driving and beyond, combining cutting-edge Computer Vision, Graph Neural Networks, and efficient inference to solve real-world perception challenges. What will your job look like: • Conduct hands-on research and development of AI and Deep Learning algorithms for real-world automotive perception tasks. • Own projects end-to-end — from concept, through research, prototyping, designing, training, and evaluating neural network architectures, to integration and scalable deployment. • Analyze challenging edge cases and continuously improve model performance in complex driving scenarios. • Collaborate with algorithm developers, software engineers, product managers and system teams across the organization. • Work with large-scale datasets and real-world driving scenarios to improve model accuracy, robustness, and runtime efficiency. • Bring your ideas into production-ready systems that have a direct, measurable impact on autonomous vehicle technologies used worldwide. All you need is: • B.Sc. or M.Sc. in Computer Science, Electrical Engineering, or a related field, with strong academic performance. • 3+ years of hands-on experience developing deep learning solutions using Python and frameworks such as PyTorch. • Solid foundation in Algorithms, Machine Learning, and Deep Learning fundamentals (Computer Vision / Graph Neural Networks – advantage). • Strong analytical skills, a sense of ownership, and the ability to work collaboratively. Nice to have: • Experience leveraging AI agents and modern productivity tools in development workflows. • Experience with cloud environments and big data tools. Mobileye changes the way we drive, from preventing accidents to semi and fully autonomous vehicles. If you are an excellent, bright, hands-on person with a passion to make a difference come to lead the revolution!

The road algorithm team is responsible for the critical and challenging task of detecting the drivable lanes on the road. We focus on Deep Learning algorithms, classical Computer Vision and Geometric Modeling algorithms. We are looking for an Algorithm Developer to help us advance our technology and push the boundaries of what's possible in autonomous driving. What will your job look like: • Develop and optimize computer vision and deep learning algorithms to accelerate data generation and labeling workflows for autonomous driving. • Apply both classical computer vision techniques and modern deep learning methods to solve large-scale data challenges. • Collaborate closely with development and annotation teams to enhance automation and ensure high-quality data. • Own the entire lifecycle from prototyping to scalable deployment within internal pipelines and tools. • Develop tools to evaluate and analyze algorithm performance, robustness, and operational efficiency. All you need is: • B.Sc. or M.Sc. in Computer Science, Electrical Engineering, or a related field, with strong academic performance. • Solid foundation in algorithms, data structures, and computer vision/deep learning fundamentals. • Practical experience developing computer vision or machine learning solutions using Python and frameworks such as PyTorch or TensorFlow – must. • Strong analytical skills, a sense of ownership, and the ability to work collaboratively. Mobileye changes the way we drive, from preventing accidents to semi and fully autonomous vehicles. If you are an excellent, bright, hands-on person with a passion to make a difference come to lead the revolution!

Mobileye is the world leader in automotive and driving assistance systems, developing the world's most advanced software technologies and hardware architectures. Mobileye is providing an end-to-end software solution for development and deploying features on its HW chip - EyeQ. The compilers team is looking for a C++ Software engineer with a passion for low level optimizations and code analysis. What will your job look like? • Develop and extend a compiler based on the LLVM infrastructure to support and optimize Mobileye's EyeQ hardware. • Implement and improve middle‑end and back‑end compiler optimizations. • Analyze generated code to improve performance and efficiency. • Perform real-world benchmark analysis to find optimization opportunities. • Collaborate with chip architects on defining and supporting future hardware generations. All you need is: • B.Sc. in Computer Science, Computer Engineering, or a related field - Must. • 3+ experience in C/C++ and Python - Must. • Fluent English communication skills, both written and spoken. • Experience with low‑level, firmware, or embedded software development and debugging. • Familiarity with compiler technologies, particularly LLVM or MLIR. • Experience analyzing benchmarks and performance data. Mobileye changes the way we drive, from preventing accidents to semi and fully autonomous vehicles. If you are an excellent, bright, hands-on person with a passion to make a difference come to lead the revolution!

We are seeking a Deep Learning Algorithm Developer with strong software engineering skills. Our team is project-oriented, meaning we are assigned significant computer vision projects and solve them using novel, state-of-the-art neural networks. Projects can be initiated both bottom-up and top-down, and they are always interesting and challenging. What will your job look like: • The job consists of a mix of algorithmic research and algorithms development, with an emphasis on deep neural networks. • You will learn and deploy state-of-the-art techniques to achieve world-class results which will allow the safe development of autonomous driving features and advanced driver assistant systems. • The work is typically done in teams and the amount of team interaction varies based on the needs and the employees' tendencies and preferences. • You will be solving algorithmic problems in many fields including mapping, and geometric problems by using heuristic solutions in addition to neural networks. All you need is: • B.Sc. in Computer Science, Electrical Engineering, or related field. • Advanced degree (M.Sc. or Ph.D) in Computer Vision, Deep Learning, or Machine Learning- advantage. • 2+ years of experience in developing DL algorithms. • Python programming skills. • Experience with training transformers in PyTorch. Mobileye changes the way we drive, from preventing accidents to semi and fully autonomous vehicles. If you are an excellent, bright, hands-on person with a passion to make a difference come to lead the revolution! Mobileye changes the way we drive, from preventing accidents to semi and fully autonomous vehicles. If you are an excellent, bright, hands-on person with a passion to make a difference come to lead the revolution!

We are looking for an M.Sc. Graduate Deep Learning Algorithm Developer to join one of our teams developing perception technologies for autonomous driving. Our group tackles diverse challenges — from object detection and scene understanding to 3D perception — using large-scale, real-world in-house datasets and state-of-the-art deep learning models. What will your job look like: • Develop and train neural networks for complex perception tasks in real-world driving environments. • Design and analyze deep learning pipelines, from data to deployment. • Collaborate with algorithm, software, and data experts to deliver production-ready models. • Research and apply new methods in computer vision, 3D perception, and multi-task learning to improve performance and efficiency. All you need is: • M.Sc. in a relevant field (Machine Learning / Computer Vision / Robotics / similar) - Must • B.Sc. from a leading university • Solid background in Machine Learning and Deep Learning • Strong Python development skills • Highly motivated, hard-working, proactive, and driven to solve challenging problems • Ability to operate in a fast-paced research & development environment Advantages: • PhD or relevant academic publications • Experience with Linux, Git, Docker, C++ • Knowledge in 3D perception, computer vision, or robotics • Industry experience working on CV and Deep Learning Mobileye changes the way we drive, from preventing accidents to semi and fully autonomous vehicles. If you are an excellent, bright, hands-on person with a passion to make a difference come to lead the revolution!

Job Description Summary The Staff Machine Learning Engineer is a senior technical leader responsible for designing, developing, and deploying production-grade AI systems for GE Healthcare medical imaging products. This role focuses on vision-language models, diffusion models, and multimodal learning, working closely with data scientists, software engineers, product leaders, and clinical experts to turn advanced AI methods into robust product capabilities. Job Description The Staff Machine Learning Engineer is a senior technical leader responsible for designing, developing, and deploying production-grade AI systems for GE HealthCare medical imaging products. This role focuses on vision-language models, diffusion models, and multimodal learning, working closely with data scientists, software engineers, product leaders, and clinical experts to turn advanced AI methods into robust product capabilities. Key Responsibilities • Design, implement, and productionize AI models for clinical applications, including vision and diffusion models. • Own end-to-end model lifecycle: data ingestion, training, evaluation, deployment, monitoring, and iteration. • Work with large-scale medical datasets, ensuring data quality, preprocessing, and efficient pipeline management. • Drive technical decisions and tradeoffs with a focus on scalability, maintainability, and real-world constraints. • Collaborate with clinical AI scientists to translate research innovations into production-ready solutions. • Stay current with advancements in vision-language modeling, GenAI, and related AI technologies. • Qualifications • Master’s or PhD in Computer Science, Electrical Engineering, Biomedical Engineering, or related field. • Significant hands-on experience building and deploying ML systems to production. • Strong experience with machine learning and deep learning frameworks (e.g., PyTorch, TensorFlow). • Solid understanding of deep learning, computer vision, and natural language processing techniques. • Prior experience working with medical imaging data is highly preferred. • Solid software engineering fundamentals, including testing, version control, CI/CD, and code reviews. • Independent, self-learner, and results-oriented. • Fluent English (speaking and writing). GE HealthCare is a leading global medical technology and digital solutions innovator. Our mission is to improve lives in the moments that matter. Unlock your ambition, turn ideas into world-changing realities, and join an organization where every voice makes a difference, and every difference builds a healthier world. GE HealthCare is an Equal Opportunity Employer where inclusion matters. Employment decisions are made without regard to race, color, religion, national or ethnic origin, sex, sexual orientation, gender identity or expression, age, disability, protected veteran status or other characteristics protected by law. We expect all employees to live and breathe our behaviors: to act with humility and build trust; lead with transparency; deliver with focus, and drive ownership – always with unyielding integrity. Our total rewards are designed to unlock your ambition by giving you the boost and flexibility you need to turn your ideas into world-changing realities. Our salary and benefits are everything you’d expect from an organization with global strength and scale, and you’ll be surrounded by career opportunities in a culture that fosters care, collaboration and support. #LI-TM1 Additional Information The job is open to men and women equally Relocation Assistance Provided: No

About Nebius: Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure. Built by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI. Listed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D. The role This role is for Nebius AI R&D, a team focused on applied research in AI. Examples of applied research that we have recently published include: • applying reinforcement learning for agent training in long-context multi-turn scenarios • dramatically scaling task data collection to power reinforcement learning for SWE agents • building a decontaminated evaluation for SWE agents that is regularly updated • investigating how test-time guided search can be used to build more powerful agents The results often lead to collaboration with adjacent teams where our research findings are applied in practice. We are currently looking for senior- and staff-level ML engineers to work on research in areas such as: • Guided search and reinforcement learning for agentic systems • Reinforcement learning for reasoning models • Web-scale problem collection for training agents • Efficient model distillation Some examples of what your responsibilities might include are: • Conducting experiments to figure out efficient ways to train a large language model on traces of interactions with various environments • Exploring methods of guided generation and search in the trajectory space • Coming up with ways to mine relevant data at web scale and figuring out efficient ways to use this data in model post-training • Conducting experiments with different reinforcement learning configurations in verifiable domains • Exploring methods to train AI agents on tasks with non-verifiable reward signals We expect you to have: • A profound understanding of theoretical foundations of machine learning and reinforcement learning • Deep expertise in modern deep learning for language processing and generation • Substantial experience with training large models on multiple computational nodes • Strong software engineering skills (we mostly use python) • Deep experience with modern deep learning frameworks (we use jax) • Strong communication and leadership abilities • Experience designing, executing, and analyzing machine learning experiments with proper statistical rigor • Ability to formulate research questions, design experiments to test hypotheses, and draw meaningful conclusions from results • Ability to document research findings clearly and contribute to technical publications or report Nice to have: • Experience with deep reinforcement learning for LLMs, including techniques such as reward modeling, DPO, PPO etc • Familiarity with important ideas in LLM space, such as RoPE, ZeRO/FSDP, Flash Attention, quantization • Bachelor’s degree in Computer Science, Artificial Intelligence, Data Science, or a related field Master’s or PhD preferred • Track record of building and delivering products (not necessarily ML-related) in a dynamic startup-like environment • Experience in engineering complex systems, such as large distributed data processing systems or high-load web services • Open-source projects that showcase your engineering prowess • Excellent command of the English language, alongside superior writing, articulation, and communication skills • Proficiency in contemporary software engineering approaches, including CI/CD, version control and unit testing Benefits & Perks: • Competitive compensation • Career growth and learning opportunities • Flexibility and ownership • Collaborative and innovative culture • Opportunity to work on impactful AI projects • International environment and talented teams What's it like to work at Nebius: Fast moving - Bold thinking - Constant growth - Meaningful impact - Trust and real ownership - Opportunity to shape the future of AI Equal Opportunity Statement: Nebius is an equal opportunity employer. We are committed to fostering an inclusive and diverse workplace and to providing equal employment opportunities in all aspects of employment. We do not discriminate on the basis of race, color, religion, sex (including pregnancy), national origin, ancestry, age, disability, genetic information, marital status, veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by applicable law. Applicants must be authorized to work in the country in which they apply and will be required to provide proof of employment eligibility as a condition of hire. If you need accommodations during the application process, please let us know.

About Nebius: Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure. Built by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI. Listed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D. The Product In a rapidly evolving world, trust in AI depends on AI agents being grounded in fresh, verified real-world data. Search is the foundation that makes this possible. We are building an agent-native search platform designed specifically for AI systems rather than human users. Our product provides programmatic, low-latency, and observable search APIs that AI agents use to retrieve, filter, and reason over real-world information at scale. The Role As a Senior ML Engineer focused on Search Optimization, you will work on improving the quality of our search product across the all parts of the search stack. You will work on problems such as query understanding, query reformulation and expansion, retrieval, ranking, reranking, and result selection. Your goal will be to identify where search quality is lost, develop better approaches, and turn them into measurable improvements in production. This is an applied ML and information-retrieval role combining experimentation with production impact. You will work with real-world queries, large-scale search systems, and evaluation signals to improve relevance, recall, freshness, and overall result quality. In this position, your responsibility will be to • Design, implement, and operate the retrieval system for a search vertical • Connect and tune the data pipeline, from ingestion to relevance tuning • Build knowledge-graph and entity-resolution layers: entity linking / NER, ontologies, and graph databases (Neo4j or similar) • Develop structured-extraction pipelines over messy, unstructured domain data • Reason about freshness and trust: model how confident we are in a fact and how stale it has become before we serve it • Define evaluation and quality metrics for relevance and drive measurable improvements • Collaborate with crawling, indexing, and ML teams to ensure retrieval and ranking requirements are met • Enable safe experimentation with retrieval, ranking, and extraction strategies You may be a good fit if you have: • 6+ years of software engineering experience, some of it in search / information retrieval • Strong IR fundamentals: inverted indexes, BM25/TF-IDF, query understanding, ranking, and evaluation (nDCG/MRR/recall@k) • Experience with vector & hybrid retrieval: ANN, dense+sparse fusion, embeddings models • Experience building structured extraction over messy/unstructured domain data • Fluent in Python and comfortable with systems-level performance work Strong candidates may also have experience with: • Knowledge graphs: entity resolution, entity linking / NER, graph DBs (Neo4j), ontologies / schema design • Owning relevance / ranking for a real product and improving it against IR metrics • Data quality, truth discovery, or systems that decide how much to trust a piece of information • Published work on IR, ranking, or knowledge graphs Benefits & Perks: • Competitive compensation • Career growth and learning opportunities • Flexibility and ownership • Collaborative and innovative culture • Opportunity to work on impactful AI projects • International environment and talented teams What's it like to work at Nebius: Fast moving - Bold thinking - Constant growth - Meaningful impact - Trust and real ownership - Opportunity to shape the future of AI Equal Opportunity Statement: Nebius is an equal opportunity employer. We are committed to fostering an inclusive and diverse workplace and to providing equal employment opportunities in all aspects of employment. We do not discriminate on the basis of race, color, religion, sex (including pregnancy), national origin, ancestry, age, disability, genetic information, marital status, veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by applicable law. Applicants must be authorized to work in the country in which they apply and will be required to provide proof of employment eligibility as a condition of hire. If you need accommodations during the application process, please let us know.

About Nebius: Nebius is leading a new era in cloud infrastructure for the global AI economy. We are building a full-stack AI cloud platform that supports developers and enterprises from data and model training through to production deployment, without the cost and complexity of building large in-house AI/ML infrastructure. Built by engineers, for engineers. From large-scale GPU orchestration to inference optimization, we own the hard problems across compute, storage, networking and applied AI. Listed on Nasdaq (NBIS) and headquartered in Amsterdam, we have a global footprint with R&D hubs across Europe, the UK, North America and Israel. Our team of 1,500+ includes hundreds of engineers with deep expertise across hardware, software and AI R&D. The role As a Senior Machine Learning Engineer on the Applied AI team at Nebius Token Factory, you will own model and endpoint optimization from model artifacts through production deployment. Your work will span model internals, quantization and model compression, speculative decoding, KV-cache optimization, inference engines, serving architecture, and benchmarking to improve latency, throughput, memory efficiency, GPU utilization, and cost per token while preserving quality and reliability. You will work with kernel and platform engineers to investigate serving problems, compare configurations, and resolve performance and quality regressions. You will evaluate model- and engine-level optimizations together with distributed inference designs, including request routing, scheduling, prefill/decode coordination, and multi-node GPU execution. Your improvements will be validated through reproducible benchmarks and safe production rollouts under real-world workloads. Your responsibilities • Own optimization projects for specific model families, customer endpoints, or serving backends. • Compare inference engines and recommend serving configurations suited to individual workloads. • Diagnose model-quality and performance regressions during production rollouts. • Improve LLM and VLM endpoint latency, throughput, memory efficiency, GPU utilization, quality, and cost per token. • Deploy, configure, benchmark, and extend engines such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, and NVIDIA Dynamo. • Develop production model-compression workflows covering quantization, quantization-aware training, distillation, low-bit serving, and accuracy recovery. • Implement or integrate speculative decoding, draft-model approaches, KV-cache optimization, prefix caching, chunked prefill, continuous batching, and disaggregated prefill/decode serving. For prefill–decode disaggregation (PDD), evaluate KV-cache transfer, worker placement, and capacity balancing to determine which workloads benefit from the architecture. • Design and improve LLM request routers and scheduling policies that balance worker utilization, queueing, request characteristics, and KV-cache locality while meeting latency and reliability targets. • Scale dense and mixture-of-experts inference across multiple GPU nodes. Select and tune tensor, pipeline, data, and expert parallelism—including wide expert parallelism (WideEP)—with attention to hardware topology, expert load balance, and communication overhead. • Build reproducible benchmark harnesses measuring TTFT, TPOT, tokens per second per GPU, p95/p99 latency, GPU memory, reliability, and cost per token. Validate architecture choices under representative traffic and consistent GPU budgets. • Collaborate with GPU kernel and platform engineers to trace bottlenecks across model code, kernels, runtime, scheduler, gateway, and cluster layers. • Produce design documents, performance reports, rollout plans, and customer-facing technical explanations. Must-haves • Strong engineering skills in Python and PyTorch. • Hands-on experience deploying or optimizing LLM, VLM, or high-throughput transformer inference. • Practical knowledge of at least one modern inference stack, such as vLLM, SGLang, TensorRT-LLM, Triton Inference Server, NVIDIA Dynamo, Ray Serve, KServe, or an equivalent internal system. • A strong understanding of transformer inference bottlenecks involving KV cache, attention, memory bandwidth, batching, parallelism, and long-context serving. • Ability to quantify trade-offs among latency, throughput, quality, utilization, and cost. • Experience designing or optimizing distributed inference system architecture, with hands-on work in one or more areas such as request routing, distributed scheduling, PDD, multi-node inference, or expert parallelism. • Strong communication and collaboration skills across research, kernel, infrastructure, product, and customer teams. Nice-to-haves • Experience with quantization-aware training, post-training quantization, FP8, INT8, INT4, NVFP4, MXFP4, AWQ, GPTQ, or SmoothQuant. • Experience with distillation, speculative decoding, EAGLE, Medusa, multi-token prediction, or related inference acceleration methods. • Experience supporting agentic workloads involving tool calling, structured outputs, streaming APIs, high concurrency, and multi-step orchestration. • Familiarity with CUDA or Triton; the role does not require kernel engineering to be the candidate’s primary specialization. • Contributions to open-source projects such as vLLM, SGLang, TensorRT-LLM, FlashInfer, LMCache, PyTorch, Triton, Ray, or KServe. • Implementation experience with cache-aware request routing, PDD, or WideEP, including diagnosing communication bottlenecks and load imbalance. • Familiarity with GPU communication libraries and interconnects, such as NCCL, NVLink, InfiniBand, or RoCE. Benefits & Perks: • Competitive compensation • Career growth and learning opportunities • Flexibility and ownership • Collaborative and innovative culture • Opportunity to work on impactful AI projects • International environment and talented teams What's it like to work at Nebius: Fast moving - Bold thinking - Constant growth - Meaningful impact - Trust and real ownership - Opportunity to shape the future of AI Equal Opportunity Statement: Nebius is an equal opportunity employer. We are committed to fostering an inclusive and diverse workplace and to providing equal employment opportunities in all aspects of employment. We do not discriminate on the basis of race, color, religion, sex (including pregnancy), national origin, ancestry, age, disability, genetic information, marital status, veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by applicable law. Applicants must be authorized to work in the country in which they apply and will be required to provide proof of employment eligibility as a condition of hire. If you need accommodations during the application process, please let us know.