Overview
We are looking for a Senior Computer Vision Engineer to build and deploy perception systems that run onboard autonomous aerial platforms. This is not offline research. Our algorithms run in real time on embedded computers, in the air, in conditions we do not control.
You will work across the full stack of the problem: classical computer vision and deep learning, camera and sensor selection, calibration, model training and evaluation, and optimization for constrained hardware. You will take your work to the field, fly it, look at the logs, and improve it. Our platforms serve both commercial and government customers across applications including inspection, mapping, search and rescue and security.
If you like hard real world problems and short feedback loops between an idea and a flight test, we want to talk with you.
Responsibilities and Duties
- Design, implement and optimize onboard perception algorithms for real time detection, temporal association and state estimation of dynamic objects from a moving platform.
- Train, retrain and evaluate neural networks for detection and classification, including dataset curation, labelling strategy and evaluation methodology.
- Optimize models and pipelines for embedded inference, working to explicit latency, throughput and compute budgets.
- Develop and maintain camera calibration and sensor synchronization procedures, including multi camera and multi sensor setups.
- Combine visual measurements with inertial and platform state data using filtering and estimation techniques for robust performance under egomotion.
- Plan and run field test campaigns. Take algorithms from bench to flight, work with pilots and integrators on site, and close the loop on real captured data.
- Build repeatable evaluation methods so that performance and accuracy are measurable across every iteration rather than judged by eye.
- Provide input into camera, lens, sensor and compute selection, and evaluate hardware options against real performance data.
- Take full ownership of computer vision deliverables. Disambiguate requirements, drive alignment across teams, keep stakeholders informed and see work through to the customer.
- Mentor and coach other engineers, and raise the bar on product quality.
Qualifications and Skills
- Degree in Computer Science, Electrical Engineering, Robotics or a related field, or equivalent practical experience.
- Strong hands on experience deploying computer vision systems on resource constrained platforms, ideally robotic or aerial.
- Solid grounding in classical computer vision: feature detection and matching, optical flow, camera models and calibration, multiple view geometry.
- Practical experience training and deploying convolutional neural networks for detection or classification, including the unglamorous parts: data collection, labelling quality, retraining loops and honest evaluation.
- Rigor about timing and synchronization across sensors. Understanding of why timestamps, exposure timing and latency matter, and experience debugging problems that turned out to be timing problems.
- Proficiency in C++ and Python, with real experience in OpenCV.
- Track record of taking computer vision work end to end, from problem definition to something running in a real deployment.
- Comfort with field work, including travel to test sites and debugging from real world logs and video.
- Ability to navigate ambiguity and lead across teams in a fast moving environment.
- Effective communication and collaboration across engineering, product and external stakeholders.
- EU citizenship required.
Nice to have
- State estimation and sensor fusion. Kalman and extended Kalman filters, IMU integration, estimation under egomotion.
- Experience with visual inertial odometry or visual SLAM, or other hard estimation work on a moving platform.
- Experience with ROS2 or similar middleware.
- Experience with embedded inference runtimes and model optimization such as quantization or pruning.
- Familiarity with GPU or NPU accelerated pipelines on embedded SoCs.
- Experience building CI or hardware in the loop infrastructure for perception regression testing.
- Background in aerial platforms, PX4 or MAVLink based systems.
Benefits
- Flexible working hours
- Stock Options
- Generous holiday allowance
- Company pension plan
- Car parking
- Enhanced maternity & paternity leave
- Mental health and wellbeing support
- Learning and development opportunities
About Auterion
We are building the leading software platform for AI-powered autonomous systems for enterprise and government customers. Our team is supporting the most important missions and solving the most challenging problems.
At Auterion, we bring together the sharpest minds who love to solve the hardest problems. Join a vibrant team built on innovation, openness, and excellence, where you’ll be empowered to develop ideas, collaborate across all levels, and make an impact that matters.
Skills Required
- Degree in Computer Science, Electrical Engineering, Robotics, or a related field, or equivalent practical experience.
- Hands-on experience deploying computer vision systems on resource-constrained platforms, ideally robotic or aerial.
- Strong grounding in classical computer vision, including feature detection and matching, optical flow, camera models and calibration, and multiple-view geometry.
- Experience training and deploying convolutional neural networks for detection or classification, including data collection, labeling, retraining, and evaluation.
- Experience with sensor timing and synchronization, including debugging timestamp, exposure-timing, and latency issues.
- Proficiency in C++, Python, and OpenCV.
- Track record of taking computer vision work from problem definition through real-world deployment.
- Comfort with field work, travel to test sites, and debugging from real-world logs and video.
- Ability to navigate ambiguity and lead across teams in a fast-moving environment.
- Effective communication and collaboration with engineering, product, and external stakeholders.
- Experience with state estimation and sensor fusion, including Kalman filters, extended Kalman filters, and IMU integration.
- Experience with visual-inertial odometry, visual SLAM, or related estimation work on moving platforms.
- Experience with ROS2 or similar middleware.
- Experience with embedded inference runtimes and model optimization, such as quantization or pruning.
- Familiarity with GPU- or NPU-accelerated pipelines on embedded systems-on-chip.
- Experience building continuous integration or hardware-in-the-loop infrastructure for perception regression testing.
- Background in aerial platforms, PX4, or MAVLink-based systems.
What We Do
At Auterion we care about providing enterprise with an ecosystem of software-defined drones, payloads, and third party applications within a single easy to use platform based on open-source standards. We’re leaders in an open-source movement bigger than ourselves and we’ve been on the same mission for over a decade, since our co-founder Lorenz Meier created Pixhawk, MAVLink, QGC, and PX4 (the world’s most widely used open-source drone autopilot operating system). Our mission is to be the drone platform of choice for enterprise, government, and drone manufacturers while accelerating the drone industry by driving forward open standards to create a common, future-proof roadmap in a thriving, open ecosystem of buyers and vendors. At Auterion, we bring together the sharpest minds who love to solve the hardest problems. Join a vibrant team built on innovation, openness, and excellence, where you’ll be empowered to develop ideas, collaborate across all levels, and make an impact that matters.
