Researcher, Locomotion

Highlights

• Push open-source humanoid Asimov from walking to running and recovery.
• Ship locomotion policies to real biped hardware, tested under real contact.
• Own balance and gait that survives pushes, slips and uneven terrain.

Ideal candidate

Hands-on roboticist who lives to see learned motion stand up on real hardware. You thrive in fast, cross-disciplinary teams, debug failures deeply, and want your work open-sourced for thousands to build on.

Requirements

• Deep hands-on experience with reinforcement learning for continuous control, legged locomotion, or whole-body control
• Track record of getting learned policies onto real robots, not only into papers or simulators
• Strong command of a physics simulator such as MuJoCo, Isaac, or similar, including reward shaping and domain randomization
• Fluency in Python and modern RL tooling, and comfort in a ROS2-based control stack
• Bias for shipping and clear thinking about why a policy fails, not just whether it does