Senior AI Robotics Research Engineer

Agility Robotics; Fremont, Salem, Pittsburgh (CA, OR, Allegheny County); Hybrid; USD 166,000 - 260,000; Full time

Benefits offered by this job

6% company match 401(k)

Stock options

Medical, dental, vision insurance

Unlimited PTO

Relocation assistance

Annual discretionary bonus

Job summary

Agility Robotics is seeking an AI/Robotics researcher to develop and test imitation learning and reinforcement learning methods for humanoid robots. You will run experiments on real hardware and translate results into production-ready policies that improve reliability and safety.

You will design locomotion, manipulation, and interaction policies, build scalable reinforcement learning infrastructure, and create new simulation environments to support training and deployment.

Qualifications

• 3+ years of experience developing and deploying learning-from-demonstration.
• Strong programming in Python with PyTorch proficiency.
• Experience with robot data collection and hardware testing for manipulation tasks.

Responsibilities

• Design, train, and deploy robust policies for locomotion, manipulation, and dynamic interactions.
• Develop core RL infrastructure, including scalable training pipelines and evaluation frameworks.
• Design and implement new simulation environments and tasks for training and deployment.
• Develop, design, and test imitation learning methods.
• Collaborate with Robotics Software and AI engineering teams to productionize policies.

Skills

Python

PyTorch

LfD

Collaboration

Fast-paced environment

Education

MS in Robotics

MS in Computer Science

Tools

DiffusionPolicy

Mujoco

Isaac Sim

C++

Job description

Agility Robotics is seeking an AI/Robotics researcher to develop and test imitation learning and reinforcement learning methods for humanoid robots. You will run experiments on real hardware and translate results into production-ready policies that improve reliability and safety.

You will design locomotion, manipulation, and interaction policies, build scalable reinforcement learning infrastructure, and create new simulation environments to support training and deployment.