Senior ML Engineer, Manipulation

Senior ML Engineer, Manipulation at Chef Robotics builds autonomous robots that operate with humans in commercial food preparation environments. You will own learning systems enabling robots to reliably pick, place, and handle diverse food classes using multiple end effectors (suction, parallel jaw, multi-finger). Responsibilities include designing and training manipulation policies (imitation learning, RL), implementing modern policy architectures (diffusion policies, transformer-based action models), building data collection pipelines (teleoperation, kinesthetic teaching, autonomous rollouts), curating datasets and training infrastructure, defining evaluation metrics and benchmarks, and hardening recovery behaviors for real-world manipulation. You will collaborate with perception and robotics engineers to validate end-to-end grasp-to-place performance across new food classes and end effector configurations, and deploy policies to real robotic hardware on physical robots in production environments. Qualifications include an MS or PhD in Robotics, Machine Learning, Computer Science, or related field (or equivalent practical experience), 5+ years in ML for robotics manipulation/visuomotor control, deep expertise in at least two areas (imitation learning, reinforcement learning, grasp estimation, or learned motion generation), strong PyTorch and Python software engineering, and a track record of end-to-end project ownership and field deployment. Nice-to-have items include experience with VLA models, diffusion policies, sim-to-real transfer, multiple end effectors, and publications in robotics venues.