{"id":72367,"title":"Robot Learning Engineer (m/f/d) VLA & Foundation Models","company":"Agile Robots SE","city":"München","region":"Bayern","location":"Munich, Bavaria, Germany","work_model":"unknown","employment_type":"unknown","employment":["full_time"],"roles":["software"],"visa":"not_mentioned","relocation":"not_mentioned","posted_at":"2026-09-09T10:30:46+00:00","tools":["Agile","ROS","Python","PyTorch"],"seniority":"unknown","years_experience_min":null,"german_requirement":"not_mentioned","german_level":"unspecified","english_requirement":"required","english_level":"unspecified","team_language":"unknown","confidence":0.4,"method":"rules","language_badge":"Not stated","language_evidence":null,"requirements_snippet":null,"url":"https://job-boards.eu.greenhouse.io/agilerobotsse/jobs/4964863101","source":"greenhouse","agency":null,"description_text":"The AI Teams at Agile Robots are looking for a Robot Learning Engineer (m/f/d) in VLA & Foundation Models, who will develop and deploy vision- and language-conditioned robot policies for real-world manipulation on physical robot platforms.\n\nYour Responsibilities\n• Policy Development: Design, train, and evaluate vision- and language-conditioned robot policies using approaches such as imitation learning, diffusion models, transformer architectures, or reinforcement learning.\n• Data Pipelines: Build workflows for collecting, structuring, and validating multimodal robot data from teleoperation, simulation, and real-world experiments, covering video, proprioception, force signals, and task outcomes.\n• Robot Integration: Define action spaces, control interfaces, temporal chunking, and evaluation protocols to ensure learned policies are compatible with real robot execution contexts.\n• Failure Analysis: Test policies in simulation and on physical robots, diagnosing failures caused by distribution shift, perception errors, contact dynamics, latency, and data quality.\n• Deployment: Integrate learned policies into robot software stacks, with attention to latency, synchronization, safety checks, fallback behavior, and runtime monitoring.\n• Research Application: Track developments in robot learning, VLA models, and foundation model methods, applying relevant advances to Agile's robot platforms and use cases.\n\nEssential Skills\n• Background: Degree in computer science, robotics, electrical engineering, or a closely related field, or an equivalent combination of research and professional experience in robot learning or embodied AI.\n• Robot Learning: Hands-on experience building or working with learning-based robot policies, including imitation learning, visuomotor control, VLA models, or closely related embodied AI methods.\n• Robotics Systems: Practical experience with robotic hardware, including real robot manipulation, ROS/ROS2, sensor integration, control interfaces, or real-world robot deployment.\n• ML Engineering: Working proficiency in Python and PyTorch, including the ability to implement models, training loops, data loaders, and evaluation pipelines beyond notebook-level prototypes.\n• Experimental Practice: Ability to design experiments, compare model variants, debug failures across the ML/robotics boundary, and iterate toward measurable performance on real tasks.\n\nBeneficial Skills\n• VLA Experience: Familiarity with VLA models or robotic foundation models such as π0, GR00T, or equivalent, including action-token or action-chunk representations.\n• Policy Deployment: Experience deploying learned models on physical robots or edge compute platforms, including latency-constrained inference pipelines.\n• Reinforcement Learning: Experience with online or offline RL for robotics, including reward design, simulation-based training, or combining RL with imitation learning.\n• Simulation: Experience with simulators such as MuJoCo, Isaac Sim, or ManiSkill and with sim-to-real transfer workflows.\n• Data Collection: Experience building or operating teleoperation systems, human-in-the-loop data collection, or intervention learning setups.\n\nWhat we offer\n\n•\nA dynamic high-tech company, combined with financial soundness and world-class investors.\n\n•\nJoin an interdisciplinary, international team with 60+ different nationalities in a collaborative work environment.\n\n•\nLots of development opportunities as we continue to grow.\n\n•\nChallenging tasks and impactful projects alongside experts that enable professional and personal growth.\n\n•\nCorporate Benefits Program covering health, mobility, and learning for 100€ net per month.\n\n•\nModern office facilities with a rooftop terrace overlooking Munich, free drinks & fruits, and regular company events contribute to a good working environment\n\nAbout us\n\nAgile Robots is a leading provider of AI-powered robotics solutions. By combining artificial intelligence and robotics, the company makes industries smarter, more flexible, and more efficient.\n\nFounded in Munich in 2018 by renowned robotics researchers from the German Aerospace Center (DLR), Agile Robots has experienced rapid global growth. Today, more than 3,500 highly skilled robotics and AI enthusiasts are employed worldwide. The company has one of the largest research and development teams in the AI and robotics industry.\n\nAgile Robots has built a unique portfolio, together with the subsidiaries BÄR Automation, Franka Robotics, idealworks, and Krause Automation, the company covers all areas of AI-driven robotics.\n\nFind out more at: https://www.agile-robots.com/en/","responsibilities_text":"• Policy Development: Design, train, and evaluate vision- and language-conditioned robot policies using approaches such as imitation learning, diffusion models, transformer architectures, or reinforcement learning.\n• Data Pipelines: Build workflows for collecting, structuring, and validating multimodal robot data from teleoperation, simulation, and real-world experiments, covering video, proprioception, force signals, and task outcomes.\n• Robot Integration: Define action spaces, control interfaces, temporal chunking, and evaluation protocols to ensure learned policies are compatible with real robot execution contexts.\n• Failure Analysis: Test policies in simulation and on physical robots, diagnosing failures caused by distribution shift, perception errors, contact dynamics, latency, and data quality.\n• Deployment: Integrate learned policies into robot software stacks, with attention to latency, synchronization, safety checks, fallback behavior, and runtime monitoring.\n• Research Application: Track developments in robot learning, VLA models, and foundation model methods, applying relevant advances to Agile's robot platforms and use cases.\nEssential Skills\n• Background: Degree in computer science, robotics, electrical engineering, or a closely related field, or an equivalent combination of research and professional experience in robot learning or embodied AI.\n• Robot Learning: Hands-on experience building or working with learning-based robot policies, including imitation learning, visuomotor control, VLA models, or closely related embodied AI methods.\n• Robotics Systems: Practical experience with robotic hardware, including real robot manipulation, ROS/ROS2, sensor integration, control interfaces, or real-world robot deployment.\n• ML Engineering: Working proficiency in Python and PyTorch, including the ability to implement models, training loops, data loaders, and evaluation pipelines beyond notebook-level prototypes.\n• Experimental Practice: Ability to design experiments, compare model variants, debug failures across the ML/robotics boundary, and iterate toward measurable performance on real tasks.\nBeneficial Skills\n• VLA Experience: Familiarity with VLA models or robotic foundation models such as π0, GR00T, or equivalent, including action-token or action-chunk representations.\n• Policy Deployment: Experience deploying learned models on physical robots or edge compute platforms, including latency-constrained inference pipelines.\n• Reinforcement Learning: Experience with online or offline RL for robotics, including reward design, simulation-based training, or combining RL with imitation learning.\n• Simulation: Experience with simulators such as MuJoCo, Isaac Sim, or ManiSkill and with sim-to-real transfer workflows.\n• Data Collection: Experience building or operating teleoperation systems, human-in-the-loop data collection, or intervention learning setups.","requirements_text":null,"status":"open","duplicate_of":null,"first_seen":"2026-11-02T21:24:42.316096+00:00","responsibilities_summary":null,"requirements_summary":null,"all_tools":["Agile","ROS","Python","PyTorch"],"posting_language":"en","evidence":[],"years_experience_max":null,"mobility_evidence":[],"model_version":"rules-8","english_badge":"English required","company_id":293}