Researcher, Manipulation
Core
Design, train, and ship reinforcement learning policies for manipulation, grasping, and dexterous, contact-rich tasks on the Asimov humanoid robot platform.
Role type
Senior IC reinforcement learning researcher (robotic manipulation)
Builds
Reinforcement learning policies for whole-body manipulation and dexterous control on real humanoid robots
Domain
Robotics, Reinforcement Learning, Humanoid Manipulation
Deliverable
production ML models
Required skills
reinforcement learning for manipulation, sim2real transfer, MuJoCo physics simulation, ROS2 control stack, Python, whole-body coordination
Preferred skills
tactile sensing, force control, teleoperation, imitation learning, open-source contributions
Technologies
MuJoCo, Isaac, ROS2, Python
Responsibilities
Design rewards and training environments for contact-heavy tasks, close the loop with real hardware telemetry, collaborate with locomotion and controls teams, open-source research outputs
Seniority
Senior, hands-on IC
