Reinforcement Learning Engineer - Locomanipulation

Join Humanoid, a company on a mission to build the world's most capable humanoid robots. As a Senior or Staff Reinforcement Learning Engineer, you will design and train reinforcement learning policies for humanoid robot control, build scalable simulation and training pipelines, and improve the robustness and sim-to-real transfer of learned policies. You will work closely with control and robotics engineers to integrate learned policies into the robot control stack and deploy and evaluate policies on real robotic systems.

• Design and train reinforcement learning policies for humanoid robot control, focusing on dynamic locomotion and loco-manipulation behaviors.
• Build scalable simulation and training pipelines, design reward functions, and improve robustness and sim-to-real transfer of learned policies.
• Deploy and evaluate policies on real robotic systems, integrate them into the control stack, and ensure stable and robust behavior in real-world conditions.