Senior Robot Learning Engineer

Senior Robot Learning Engineer (Manipulation)Chicago, IL| On site | Up to $180k + equity | Visa sponsorship and relocation supportThe companyA well funded robotics company building AI powered robots to support the labor workforce.The roleYou’ll own how the robots learn and perform physical skills: the data pipeline that captures how people do the work, the policies that learn from it, and the executor that runs every action on the robot, classical or learned, behind one interface.What you’ll doDefine how demonstrations are captured: teleop rigs (leader arms, VR) and egocentric capture of people doing the workOwn the robot learning data pipeline: synced observations and actions, labelling, dataset versioning and quality checksSet the policy architecture: a shared vision and force backbone with task conditioned heads, so a new skill needs a few demos, not a new modelTrain with imitation learning, diffusion or transformer policies and VLAs, using RL where the reward is clearBuild the training and evaluation loop in sim and on real robots, with held out evals that gate deploymentSolve manipulation of deformable materials: cable, tape, membraneOwn the actuate executor, with classical control and learned policies behind one contract so the planner can pick eitherBuild the compliance layer for contact rich work (nailing, pressing, taping, insertion) with force and impedance controlDeploy policies on the robot within real time and safety limits, and build recovery for common failuresLead and mentor learning and manipulation engineers, while still writing production code and testing on real robots every weekWhat you’ll bring5+ years in robotics or ML, including learned manipulation policies deployed on real hardwareDeep experience with imitation learning and RL, and a clear view of when to use eachForce and impedance control for contact rich manipulationBuilt a robot learning data pipeline: teleop capture, labelling, versioning, evaluationPyTorch from dataset to deployed policyStrong Python and C++, ROS2, Linux, Docker, CI/CDA record of setting technical direction and mentoring engineersNice to haveMS or PhD in Robotics, ML or CSVLAs or other robot foundation modelsDiffusion Policy, ACT or similar visuomotor architecturesDeformable object manipulation (cable, textile, tape)Bimanual or dexterous manipulationSim to real with Isaac Sim or MuJoCoTeleop systems: leader/follower arms, VR, egocentric captureDatasets in MCAP or rosbagContact rich assembly, finishing or construction workWhat’s on offerBase salary up to $180KEquityComprehensive benefitsVisa sponsorship and relocation supportDirect access to robots, sensors and manufacturing environments every weekA rare problem: teaching robots the trades that build homes, on factory and field hardware