Job description

Figure is an AI robotics company developing autonomous general-purpose humanoid robots. The goal of the company is to ship humanoid robots with human level intelligence. Its robots are engineered to perform a variety of tasks in the home and commercial markets. Figure is headquartered in San Jose, CA. We are looking for a Reinforcement Learning Engineer to develop, train, deploy, and evaluate advanced reinforcement learning algorithms for whole body control of our humanoid robot. Responsibilities: Develop, train, and deploy reinforcement learning algorithms for whole body control. Determine the observations, actions, and model types that unlock maximum performance. Identify and close the most important sim-to-real gaps. Define, test, and evaluate performance metrics for learned policies. Harden the control stack to ensure rock solid robustness. Requirements: Strong background in dynamics and control, ideally of legged robots. Experience with reinforcement learning algorithms for robotics: PPO, SAC, etc. Experience tuning hyperparameters and cost functions for these RL algorithms. Familiarity with common RL techniques such as: domain randomization, curriculum learning, reward shaping, etc. Capable of leading complex controls projects and mentoring junior engineers. Bonus Qualifications: Experience with behavior cloning techniques (e.g. distillation). The US base salary range for this full-time position is $150,000 to $350,000 per year. The pay offered for this position may vary based on several individual factors, including job-related knowledge, skills, and experience. The total compensation package may also include additional components/benefits depending on the specific role. This information will be shared if an employment offer is extended.

Requirements

Must-haves

Develop, train, and deploy reinforcement learning algorithms for whole body control.
Determine the observations, actions, and model types that unlock maximum performance.
Identify and close the most important sim-to-real gaps.
Define, test, and evaluate performance metrics for learned policies.
Harden the control stack to ensure rock solid robustness.
Strong background in dynamics and control, ideally of legged robots.
Experience with reinforcement learning algorithms for robotics: PPO, SAC, etc.
Experience tuning hyperparameters and cost functions for these RL algorithms.
Familiarity with common RL techniques such as: domain randomization, curriculum learning, reward shaping, etc.
Capable of leading complex controls projects and mentoring junior engineers.
Experience with behavior cloning techniques (e.g. distillation).

Nice-to-haves

None flagged.

Application prep

Use the role’s language and application details while tailoring your materials.

Keywords to mirror

Platform: greenhouse
Effort: quick