Senior AI Robotics Engineer — Humanoid RL & Control

Agility Robotics; Colorado; Hybrid; USD 187,000 - 292,000; Full time

Benefits offered by this job

401(k) Plan with company match

Equity stock options

Company-paid medical, dental, vision

Flexible work arrangements

Relocation assistance

Job summary

Agility Robotics is seeking an AI Controls Engineer to advance reinforcement learning for Digit’s locomotion, manipulation, and whole-body control. You will integrate perception, build scalable training pipelines, and create new simulation environments to validate policies before deployment in real robots.

You’ll work with on-robot software teams in a fast-paced, safety-conscious environment, contributing to production-quality code and robust control systems for real-world facilities.

Qualifications

• 4+ years experience deploying RL for robotics.
• Strong Python and PyTorch skills.
• Experience with perception-in-the-loop control and sim-to-real transfer.

Responsibilities

• Design, train, and deploy robust RL policies for locomotion, manipulation, and whole-body control.
• Integrate perception into RL to achieve obstacle-aware, collision-free motion.
• Develop and maintain core RL infrastructure and training pipelines.
• Design and implement new simulation environments for training and evaluation.
• Collaborate with on-robot software and deployment teams to ship production-quality policies.

Skills

Reinforcement learning

Python

PyTorch

Robotics systems

Simulation and sim-to-real

Education

MS or PhD in Robotics or related field

Tools

Mujoco-Warp

Isaac

Job description

Agility Robotics is seeking an AI Controls Engineer to advance reinforcement learning for Digit’s locomotion, manipulation, and whole-body control. You will integrate perception, build scalable training pipelines, and create new simulation environments to validate policies before deployment in real robots.

You’ll work with on-robot software teams in a fast-paced, safety-conscious environment, contributing to production-quality code and robust control systems for real-world facilities.