Computer Vision Engineer

Job description

Job responsibilities

• Implement and optimize onboard perception algorithms for real time detection, temporal association and state estimation of dynamic objects from a moving platform.
• Integrate new camera modules onto our platforms and validate them against real requirements: image quality, timing, latency and behavior in the conditions we actually fly in.
• Build repeatable test and evaluation procedures so that camera and algorithm performance is measured rather than judged by eye, and comparable across units, builds and iterations.
• Run and improve camera calibration and sensor synchronization procedures, including multi camera and multi sensor setups.
• Profile and optimize pipelines for embedded inference against explicit latency, throughput and compute budgets, and evaluate or retrain detection models on real captured data.
• Support field test campaigns. Take algorithms and cameras from bench to flight, work alongside pilots and integrators on site and close the loop on real captured data.
• Own your deliverables end to end, contribute input into camera, lens and sensor selection, and keep the team informed on progress and risks.

Job requirements

• Degree in Computer Science, Electrical Engineering, Robotics or a related field, or equivalent practical experience.
• Experience building computer vision systems, with exposure to resource constrained or embedded platforms.
• Working knowledge of classical computer vision: feature detection and matching, optical flow, camera models and calibration, multiple view geometry.
• Practical experience with cameras as hardware, not just as a source of frames. Sensor and lens behavior, exposure, timing and what goes wrong when a new module arrives.
• Proficiency in C++ and Python, with real experience in OpenCV.
• Evidence of taking a project from problem definition to something that actually ran on hardware, and comfort doing that in the field alongside pilots and real logs.