Agent Engineer jobs in Tel Aviv-Yafo

Description What you'll own Fig's product is built around an AI agent that security analysts and detection engineers work with directly. It investigates coverage questions against live enterprise security data, authors and tests detection logic, and tunes noisy alerting. That agent is already in production with enterprise design partners. Now we need to make it dependable and scalable enough for GA. You will own that evolution: the agent architecture, its evaluation and quality system, and the production engineering around it. This is a hands-on senior IC role with real architectural authority - you set the technical direction and you write the code. The agent operates inside customer security environments, where a wrong action can become a customer incident. Correctness, isolation, observability, and evaluation are not polish. They are the product. What you'll be doing • Agent architecture: Design the evolution from today's production single-agent system to a multi-agent one: orchestration, task decomposition, runtime and framework choices, and a migration path that does not break what design partners already rely on. • Agent capability: Own the prompts, context, skills, and tool design that make the agent genuinely good at detection engineering across multiple security platforms, not just plausible-sounding. • Evaluation platform: Build the harnesses, judges, and golden datasets that turn "the agent feels better" into a number, plus the CI gates that keep regressions from shipping. • Reliability and safety: Keep long-running agentic sessions healthy in production, and build the isolation and guardrails required of an agent working inside enterprise security environments. • Production debugging: Work real failures from production traces, and turn each one into an eval case that can never regress silently. • Technical direction: Make the calls on architecture, sequencing, and quality bar and be accountable for the outcome, including raising how AI-natively the whole team builds. • Cross-team partnership: Partner with product and customer-facing teams on what the agent should do, and with platform teams on the data and integrations it depends on. Requirements What you'll need • Senior engineering depth: You have 6+ years of experience building and operating production software, with strong backend and distributed-systems fundamentals and experience designing APIs and services. • Shipped agents, not demos: You have taken an LLM agent system with tool use, multi-turn interaction, and planning to real users, and you can talk concretely about how it failed and what you did about it. • Architectural judgment: Informed opinions on single-agent vs. multi-agent design, orchestration patterns, and the current framework and SDK landscape, with the pragmatism to pick the boring option when boring wins. • Eval discipline: You have built or owned evaluation for an LLM system, including golden datasets, LLM-as-judge with calibration, and regression gates in CI, and you can quote the metrics you moved. • Tool design instincts: You know when a deterministic tool beats a model call, how to design tool contracts an LLM will not misuse, and how to keep cost and latency under control. • Distributed systems fluency: Streaming, stateful services, and the operational instincts to keep long-running agent sessions alive in production. • Ownership in ambiguity: You can lead an area as a hands-on IC in an early-stage environment with little existing structure. Security domain experience such as SIEM platforms, SOC workflows, detection engineering, or security query languages, and experience with modern agent SDKs and protocols such as MCP, are strong advantages.

The world of payment processing is rapidly evolving, and businesses are looking for loyal and strategic partners, to help them grow. Meet Nuvei, Nuvei is the global fintech building the infrastructure for every payment, everywhere. Its modular, flexible, and scalable technology enables leading companies to accept next-generation payments, offer all payout options, and benefit from card issuing, banking, risk, and fraud management services. Connecting businesses to their customers in more than 200 markets, with local acquiring in 52 markets, 150 currencies, and over 720 alternative payment methods, Nuvei provides the technology and insights for customers and partners to succeed locally and globally through one integration. At Nuvei, we live our core values, and we thrive on solving complex problems. We’re dedicated to continually improving our product and providing relentless customer service. We are always looking for exceptional talent to join us on the journey! Your Mission The Agentic Engineering Director serves as a senior technical leader and authority responsible for advancing agentic software engineering and establishing Agentic Delivery Lifecycle (ADLC) capabilities as a core engineering discipline. The role will define standards, governance models, platforms, evaluation frameworks and reusable capabilities required to scale agentic-native software development. You will be partnering with Engineering, Product, Enterprise Architecture, Platform Engineering, Information Security, Data, DevOps, and AI teams. You will also be managing an Agentic engineering group as part of your day-to-day. Key Responsibilities Agentic and Technical Leadership and Management • Define engineering standards and best practices for agentic delivery. • Lead a group of Agentic Engineers. • Lead lighthouse implementations and mentor engineers from other teams. • Evaluate emerging models, frameworks and agentic platforms. • Create engineering accelerators and implementation playbooks. ADLC Ownership and Evolution • Define and continuously improve ADLC standards. • Establish delivery patterns, control gates and certification requirements. • Own enterprise evaluation frameworks and agentic engineering harnesses. • Define benchmarking, regression testing and security evaluation standards. • Establish auditability, traceability, observability and rollback requirements. • Embed ADLC controls into CI/CD and operational platforms. Agentic Platforms and Developer Experience • Define requirements for enterprise agentic platforms. • Guide the adoption of Code Agents. • Define model routing, context management, memory services and AI gateways. • Establish platform security, observability and resiliency requirements. Agents, Skills and MCP Ecosystem • Define standards for approved agents, approved skills, workflows and MCP services. • Establish enterprise registries and certification frameworks. • Define prompt governance and lifecycle management. • Guide onboarding, monitoring, optimisation and retirement processes. Governance, Security and Responsible AI • Define controls for hallucinations, prompt injection and insecure code generation. • Protect intellectual property, data and regulated workloads. • Define responsible AI requirements and risk acceptance processes. • Lead incident reviews and corrective actions. Engineering Transformation and Adoption • Create adoption playbooks, academies and communities of practice. • Define capability models and career frameworks. • Measure adoption and maturity outcomes. Value Realisation and Cost Management • Track productivity, quality, release frequency and developer experience. • Measure effectiveness of agents, skills and workflows. • Optimise token usage, model routing and platform efficiency. Requirements • 10+ years of software engineering experience. • 5+ years in SW management roles. • Strong technical leadership and people management skills • Deep expertise in ADLC, cloud native architecture, CI/CD, and observability. • Expert proficiency with Code Agents and Agents Frameworks. • Experience building evaluation harnesses, benchmarking systems, and governance frameworks. • Pragmatic, data-driven, and outcomes-focused. • Champion of engineering excellence and responsible AI. Nuvei is an equal-opportunity employer that values diversity, collaboration, and innovation. We’re committed to creating an inclusive environment and look forward to welcoming passionate professionals to our team. Join us on this exciting journey! Benefits: • Private Medical Insurance. • Hybrid working model (office and home). • Global bonus plan. • Volunteering programs. • Prime office location near the Tel Aviv train station. ***Our recruitment process may use automated tools, including AI, to support application management and candidate shortlisting

The world of payment processing is rapidly evolving, and businesses are looking for loyal and strategic partners, to help them grow. Meet Nuvei, Nuvei is the global fintech building the infrastructure for every payment, everywhere. Its modular, flexible, and scalable technology enables leading companies to accept next-generation payments, offer all payout options, and benefit from card issuing, banking, risk, and fraud management services. Connecting businesses to their customers in more than 200 markets, with local acquiring in 52 markets, 150 currencies, and over 720 alternative payment methods, Nuvei provides the technology and insights for customers and partners to succeed locally and globally through one integration. At Nuvei, we live our core values, and we thrive on solving complex problems. We’re dedicated to continually improving our product and providing relentless customer service. We are always looking for exceptional talent to join us on the journey! Your Mission As an Agentic Engineer, you will help drive the organization’s adoption of agentic software engineering and contribute to establishing Agentic Delivery Lifecycle (ADLC) practices across the technology organization. You will operate within an agentic-native delivery model, using approved agents, skills, workflows, and automated platforms throughout the software lifecycle, while working closely with Product, Engineering, Platform Engineering, Enterprise Architecture, Information Security, Data, DevOps, and AI teams. Responsibilities: Agentic Software Development • Design, build, test, deploy, operate, and modernize production-grade software using agentic engineering practices. • Collaborate with autonomous and semi-autonomous agents across requirements, architecture, implementation, testing, documentation, and operations. • Direct, supervise, validate, and improve agent-generated outputs. • Review and validate agent-generated architecture, code, test suites, runbooks and deployment plans. • Apply risk-based human supervision and intervention controls. • Contribute reusable engineering accelerators, workflows and implementation patterns. Agentic Delivery Lifecycle (ADLC) • Apply ADLC practices across requirements analysis, architecture, coding, review, testing, security validation, documentation, release management, deployment, production operations, incident response and modernization. • Integrate agentic workflows with source control, CI/CD, testing frameworks and observability platforms. • Develop, maintain, and own agentic engineering harnesses for validation, benchmarking, regression testing, security evaluation, and certification. • Build evaluation frameworks measuring quality, reliability, safety and business effectiveness. • Establish measurable quality gates and production-readiness criteria. • Ensure traceability, auditability, versioning, rollback and operational transparency. • Support monitoring, logging and observability. • Contribute to the continuous evolution of ADLC standards. Agentic Platforms and Developer Experience • Support adoption of Code Agents. • Provide secure access to approved models, repositories, APIs and enterprise knowledge. • Support model routing, context management, memory services and execution environments. • Contribute to golden paths, reusable platform services and self-service capabilities. Agents, Skills, and MCP Ecosystem • Design and maintain reusable enterprise agents, specialized skills and workflows. • Build integrations using enterprise APIs and MCP services. • Support registries for approved agents, approved skills, approved prompts, approved workflows and approved MCP services. • Support lifecycle management including certification, ownership, versioning and retirement. Security, Governance, and Production Assurance • Implement controls addressing hallucination risk, prompt injection, insecure code generation and model misuse. • Ensure compliance with engineering, security, privacy and regulatory requirements. • Maintain ownership, monitoring, testing, audit trails and rollback capabilities for production agents. Engineering Adoption and Enablement • Support implementation playbooks and adoption frameworks. • Participate in training programs, communities of practice and enablement initiatives. • Mentor engineers adopting agentic-native development practices. Value Realization and Continuous Improvement • Measure and improve productivity, cycle time, software quality, release frequency and developer experience. • Track effectiveness of agents, skills, prompts, workflows and MCP services. • Identify opportunities to reduce manual engineering effort through automation. Requirements: • 7+ years of software engineering experience. • Experience with cloud-native applications and Azure, AWS or Google Cloud. • Strong understanding of ADLC, CI/CD, DevOps and software quality processes. • Understanding of LLMs, RAG, tool calling, context management, memory management and agent orchestration. • Hands-on experience with Code Agents and Agents Frameworks. • Experience with evaluation harnesses, benchmarking systems and quality assurance frameworks. Nuvei is an equal-opportunity employer that values diversity, collaboration, and innovation. We’re committed to creating an inclusive environment and look forward to welcoming passionate professionals to our team. Join us on this exciting journey! Benefits: • Private Medical Insurance. • Hybrid working model (office and home). • Global bonus plan. • Volunteering programs. • Prime office location near the Tel Aviv train station. Our recruitment process may use automated tools, including AI, to support application management and candidate shortlisting

Luna is a new startup inside monday.com Agent Labs, founded and run by monday.com's CEO, the program that spins up independent startups from scratch. Each one runs like a seed-stage company: a tiny team, a real product, real users, with monday.com's backing and distribution. Luna already has a live product, a pile of open problems nobody has answered yet, and no layers between you and the person making the calls. We're hiring the engineer who builds it. You work directly with the founder, monday.com's CEO. Decisions happen in the conversation, not in a roadmap review. You own the engineering. The founder owns the product. What we're building Meet Luna, the first generation of autonomous agents, which proved that agents can do real work. It also proved they broke. Unbounded self-coding that can touch any key. Everything is riding on raw LLM reasoning, so execution drifts. No way to see what actually happened. Luna is the second generation. It still learns and improves itself, but on a scaffold built for trust: Deterministic workflows, the agent writes and refines, then runs on a real engine instead of re-reasoning every time. A one-way vault. Secrets resolve below the plugin layer and never enter the model's context. Rollback on every change, an audit trail on every action, and approval gates on anything sensitive. Everything else is a plugin: tools, channels, skills, isolated per agent. Luna isn't a chatbot. You describe the goal, it builds the workflow, you correct it, and it runs reliably next time. A private Luna spins up in about a minute today. There's no playbook yet for what a good agent is in this context. We're writing it with real use cases and real constraints. That's the job. Who we're looking for An experienced builder at heart. You'd rather ship the thing than pitch it. This is an engineering role, not a founder track. Instincts about agents. Before writing a line, you ask what the model must never be allowed to touch, how you'd know it failed, and what happens when it does. Shipping ten agents isn't required. Having thought hard about one is. Independent. Hand you something vague, and you come back with something that works. Strong fundamentals in distributed systems and reliability, with production experience. Nice-to-have: LLM tooling in production, tool use, sandboxing, and evals. A security-minded way of building.