Robot Learning Engineer | Humanoid
Core
Post-train manipulation policies using behavior cloning and reinforcement learning, managing the full loop from data collection to deployment on real humanoid robots.
Role type
Senior/Staff Individual Contributor Robot Learning Engineer
Builds
Manipulation policies for HMND-01 humanoid robots
Domain
Robotics, Reinforcement Learning, Deep Learning
Deliverable
production ML models
Required skills
Behavior cloning, Reinforcement learning, Low-level robot control, Neural network post-training, Deep learning infrastructure (PyTorch/JAX), Data preprocessing, Simulation-to-real transfer, Software engineering
Preferred skills
VLA models (OpenVLA, Physical Intelligence), RL for robotics, PhD/Postdoc from top robotics/ML program
Technologies
PyTorch, JAX, OpenVLA, Physical Intelligence (π)
Responsibilities
Post-train manipulation policies with behavior cloning and RL; Set up RL training on digital twins and iterate reward design; Drive data collection strategy and define data quality standards; Design data preprocessing strategies; Expand observation and action spaces; Collaborate with controls teams on motion smoothness; Feed hardware limit insights into design cycles.
Seniority
Senior/Staff, hands-on IC
