Computer Vision Engineer jobs in Israel

Description Regulus is an agile defense-tech startup tackling the most complex challenges in counter-drone and uncrewed defense. With hundreds of combat-proven systems deployed by the IDF and global partners, we are now engineering the next generation of C-UxS (Counter-Uncrewed Systems). We leverage advanced electronic warfare and kinetic measures to detect and neutralize hostile threats. If you want to push technological boundaries while safeguarding Israel and our allies, join us at this pivotal stage of our growth. If you're looking for a role that combines deep technology, ownership, and real-world impact - this is your opportunity. You'll work on 0→1 development of next-generation computer vision capabilities, addressing operational challenges for which no proven solutions currently exist. Key Responsibilities: • Drive end-to-end computer vision solutions from concept and research through deployment and operational validation • Develop detection, classification, and tracking algorithms • Improve performance on small and distant aerial targets • Build and maintain training datasets and evaluation tools • Optimize models for real-time operational performance • Collaborate with software, hardware, and systems engineering teams Requirements • Strong background (3+ years experience) in computer vision and deep learning • Proven ability to independently design, develop, and deliver computer vision solutions from scratch • Experience processing real-time video from EO/IR, thermal, or surveillance cameras • Hands-on experience with detection and tracking models (YOLO, Transformer, or similar) • Proficiency in Python with PyTorch or TensorFlow • Proficiency in C++ • Performance Optimization: Experienced in multi-threaded programming and GPU acceleration to improve computational efficiency • Familiarity with small-object and long-range detection, image enhancement, and low-SNR conditions • Working knowledge of OpenCV, GStreamer, RTSP streams, and Linux Advantages: • Significant advantage for experience with airborne platforms, UAVs, UAS, loitering munitions, missile systems, aerial target tracking, or other airborne defense applications • Experience in drone detection, defense systems, radar/EO sensor fusion, or autonomous systems • C++ and production deployment experience

Description Exodigo is the leading underground mapping solution for non-intrusive discovery. Our platforms combine multi-sensor fusion, 3D imaging, and AI technologies to create complete, accurate underground maps that enable confident decision-making for customers across the built world. We transform the project lifecycle for our customers, who include key community stakeholders in the utilities, transportation and government sectors. Our Algorithms group is a highly multidisciplinary group at the core of our data processing and detection capabilities, integrating physics, signal processing, computer vision, classical algorithms, and AI models to meet our unique requirements. Within this group, the Computer Vision Team analyzes above-ground environments from visual and multi-sensor data, and its outputs feed directly into the accuracy and completeness of the maps we deliver. Job description As a Computer Vision Engineer at Exodigo, you will work on problems where imagery meets the physical world. Our systems observe real above-ground environments and have to produce results that are accurate in real-world coordinates — which means the work lives in the transition between 2D imagery and 3D space: reconstruction, localization, depth, registration, and geometric reasoning about what the sensors actually saw. The core of the role is solid computer vision engineering. Detection, segmentation, tracking, and the unglamorous work of making these tasks accurate and robust on messy real-world data are the backbone of what we build. Our stack is modern and constantly evolving — we adopt new methods as the field produces them, and we care more about whether something works on our data than about how new it is. The loop here is short — what you build reaches our mapping experts and makes an impact! Key Responsibilities • Own the development of vision algorithms end to end — from framing the problem using real data, through model design and iteration, to results that meet our accuracy requirements in production. • Develop computer vision algorithms that turn imagery and multi-sensor data into a reliable interpretation of real environments — the scene understanding that our mapping outputs depend on. • Work on the 2D-to-3D problem: geometric reasoning, reconstruction, localization, depth, and registration of visual data to real-world coordinates. • Rapidly prototype, benchmark, and refine models against our own data and accuracy requirements. • Work closely with our Mapping and Engineering experts to validate real-world robustness, and with the Software team to turn prototypes into production-grade systems. Requirements • 4+ years of industry experience developing computer vision and machine learning algorithms. Academic research experience counts in addition to this, not instead of it. • Strong spatial intuition and hands-on experience with the transition between 2D and 3D. This is a core requirement — we expect you to have worked on problems such as navigation, mapping, 3D reconstruction, photogrammetry, localization, depth estimation, or something similar in spirit. • Solid experience with core computer vision tasks such as detection, segmentation, tracking, or registration, including the practical work of making them accurate and robust on real, imperfect data. • Strong understanding of modern deep learning architectures, including transformer-based and multimodal models — how they are built and where each one fits, even if your own hands-on experience has been elsewhere. • Strong proficiency in Python and the standard scientific and computer vision stack: NumPy, SciPy, OpenCV, and PyTorch. • B.Sc. in Electrical Engineering, Computer Engineering, Computer Science, or a similar field. Preferred Qualifications • M.Sc. or Ph.D. in a relevant field. • Experience solving problems that combine text and imagery, such as document analysis. • Experience with point-cloud analysis or LiDAR data. • Experience in aerial, orthophoto, or satellite image analysis, or in geolocation problems. • Familiarity with cloud development environments, particularly AWS.