Robot Perception/ML Engineer (f/m/d) Autonomous Mobile Robots

Job description

Your tasks You develop and improve perception models for autonomous mobile robots, including object detection, obstacle classification, and free-space estimation You drive data-centric machine learning by scaling automated labeling, leveraging fleet data, and closing the sim2real gap through synthetic data and simulation-based evaluation You own model performance by defining benchmarks, tracking key metrics, and continuously improving real-world and benchmark results You deploy and validate perception models within our ROS-based robot software stack, ensuring reliable performance on real vehicles You collaborate closely with navigation, controls, and fleet software teams to deliver robust perception capabilities that enable autonomous operation Requirements You bring 2–5 years of professional and hands-on experience in robotics perception, computer vision, or machine learning You have strong Python skills; experience with C++ is a plus You have hands-on experience training and evaluating neural networks (PyTorch or similar) and follow a data-centric approach to improving model performance You have practical experience with synthetic data, simulation for ML, auto-labeling, active learning, or domain adaptation You apply a rigorous approach to model evaluation and understand how to measure real-world performance effectively You are familiar with ROS and Linux-based development environments You have a pragmatic engineering mindset and enjoy shipping, measuring, and iterating What we have to offer Cutting-edge technology : As pioneers in robotics we are able to navigate and manipulate without rails and guides and offer solutions to processes that no one could automate ever before! Team : We are an international team with more than 25 nationalities. You’ll work in a team with exceptionally smart, humble, collaborative and hardworking individuals. Culture : Come as you are! Join a vibrant, inventive, and diverse team that values collaboration over hierarchy. To innovate you need to fail from time to time — we always learn and improve. Workplace : Our office is located near the S‑Bahn station “Hirschgarten”. We work in a loft-style office with great equipment, our own workshop and testing area. Full Board : You don’t feel like thinking about what you want to have for lunch tomorrow, not to mention preparing it? Luckily, our french cook treats us with a freshly coo…