Reinforcement Learning Engineer, Whole Body Control
$150k - $350k • San Jose, CA
Posted 9d ago
Job Location
San Jose, CA
Tech Stack
Remote Work Policy
On-site
Categories
Machine Learning Engineer
About the job
Figure is an AI robotics company developing autonomous general-purpose humanoid robots with the goal of shipping robots with human-level intelligence. These robots are engineered to perform a variety of tasks in both home and commercial markets. We are seeking a Reinforcement Learning Engineer to focus on the development, training, deployment, and evaluation of advanced reinforcement learning algorithms specifically for the whole-body control of our humanoid robots.
Responsibilities
- Develop, train, and deploy reinforcement learning algorithms for whole-body control.
- Determine optimal observations, actions, and model types for maximum performance.
- Identify and address key sim-to-real gaps.
- Define, test, and evaluate performance metrics for learned policies.
- Ensure robustness of the control stack.
Requirements
- Strong background in dynamics and control, ideally for legged robots.
- Experience with reinforcement learning algorithms for robotics (e.g., PPO, SAC).
- Experience tuning hyperparameters and cost functions for RL algorithms.
- Familiarity with common RL techniques like domain randomization, curriculum learning, and reward shaping.
- Ability to lead complex controls projects and mentor junior engineers.