RL Engineer | Humanoid
Core
Build high-performing, robust manipulation policies using reinforcement learning in simulation and on real hardware for humanoid robots.
Role type
Senior individual contributor RL engineer (robotics manipulation)
Builds
Manipulation policies for the HMND-01 humanoid robot platform
Domain
Robotics, Reinforcement Learning, Vision-Language-Action models
Deliverable
production ML models
Required skills
Reinforcement learning, Deep learning, Python, PyTorch or JAX, Model training (LLMs/VLMs/generative models), Simulation environment design, Sim-to-real transfer, Trajectory collection, Pipeline setup
Preferred skills
Robotics simulators (Isaac Sim, MuJoCo), Large-scale RL infrastructure (Ray), Open VLA frameworks (OpenVLA, Physical Intelligence)
Responsibilities
Train language- and vision-conditioned manipulation policies with RL in simulation and real world; Build diverse manipulation task suites in simulation; Collect trajectories for behaviour cloning; Set up real-world RL training pipelines; Develop sim-to-real transfer methods
Seniority
Senior, hands-on IC
