RL Engineer - Whole-Body Control for Humanoid Robots

Figure AI; San Jose (CA); On-site; USD 150,000 - 350,000; Full time

Job summary

Figure AI, a San Jose-based AI robotics company, is seeking a Reinforcement Learning Engineer to develop, train, deploy, and evaluate advanced RL algorithms for whole body control of our humanoid robot.

You will determine observations, actions, and model types to maximize performance, close sim-to-real gaps, and define metrics for learned policies while mentoring junior engineers on complex control projects.

Qualifications

• Strong background in dynamics and control, ideally legged robots.
• Experience with RL algorithms for robotics (PPO, SAC, etc.).
• Ability to lead complex controls projects and mentor junior engineers.
• Familiarity with domain randomization, curriculum learning, reward shaping, etc.

Responsibilities

• Develop, train, and deploy reinforcement learning algorithms for whole body control.
• Determine observations, actions, and model types that unlock maximum performance.
• Identify and close important sim-to-real gaps.
• Define, test, and evaluate performance metrics for learned policies.
• Harden the control stack to ensure rock solid robustness.

Skills

Dynamics and control

RL for robotics

Mentoring

Hyperparameter tuning

Domain randomization

Curriculum learning

Reward shaping

Tools

PPO

SAC

Job description

Figure AI, a San Jose-based AI robotics company, is seeking a Reinforcement Learning Engineer to develop, train, deploy, and evaluate advanced RL algorithms for whole body control of our humanoid robot.

You will determine observations, actions, and model types to maximize performance, close sim-to-real gaps, and define metrics for learned policies while mentoring junior engineers on complex control projects.