Reinforcement Learning Engineer, Whole Body Control

What you'll do

• Develop, train, and deploy whole-body-control reinforcement learning algorithms; select observations, actions, and model types.
• Identify and address sim-to-real gaps, and define and evaluate learned-policy metrics.
• Harden the control stack for robustness; lead controls projects and mentor junior engineers.

What they ask for

• Strong background in dynamics and control, ideally for legged robots.
• Experience with robotics reinforcement learning algorithms such as PPO and SAC.
• Experience tuning hyperparameters and cost functions for reinforcement learning algorithms.
• Familiarity with domain randomization, curriculum learning, and reward shaping; ability to lead complex controls projects and mentor junior engineers.

Nice to have

• Experience with behavior cloning techniques, such as distillation.

Pay

$150,000 to $350,000 per year (USD base salary)

Tools

PPO, SAC

AI focus

Developing and training reinforcement learning algorithms for humanoid whole-body control, including learned policies and sim-to-real transfer.