Reinforcement Learning Engineer Whole Body Control
Figure is an AI robotics company developing general-purpose humanoid robots and its Helix vision-language-action AI system.
Funding history
About Figure
Figure develops and deploys general-purpose humanoid robots for commercial and household tasks. Its current Figure 03 robot is powered by Helix, an onboard generalist vision-language-action model; the company also operates the Index data-collection service.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will develop, train, deploy, and evaluate reinforcement learning algorithms for humanoid whole-body control. You will select observations, actions, and model types; close sim-to-real gaps; define policy metrics; and strengthen the control stack for robust performance.
Requirements
- 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
Responsibilities
- Develop, train, and deploy reinforcement learning algorithms for whole-body control
- Determine observations, actions, and model types for maximum performance
- Identify and close sim-to-real gaps
- Define, test, and evaluate performance metrics for learned policies
- Harden the control stack for robustness