Agility Robotics
Senior AI Software Engineer, Reinforcement Learning
$187K–$292K
Hybrid- Any Office (Fremont, CA, Salem, OR, or Pittsburgh, PA) +3 · Senior · Full-time · Posted Jul 28, 2026
- Location
- Hybrid- Any Office (Fremont, CA, Salem, OR, or Pittsburgh, PA)
Fremont, California, United States
Pittsburgh, Pennsylvania, United States
Salem, Oregon, United States - Experience
- 4+ years developing and deploying RL policies for robotics applications.
- Visa sponsorship
- Applicants must have current authorization to work in the United States.
About the job
Develops and deploys reinforcement-learning controllers for Digit’s locomotion, manipulation, and whole-body control, integrating perception and supporting production deployment.
What you'll do
- Design, train, and deploy RL policies for robot control and dynamic interactions.
- Integrate perception into control policies and develop simulation tasks, training pipelines, and evaluation frameworks.
- Collaborate with deployment teams to deliver production-quality policies on Digit.
What they ask for
- Strong Python skills and hands-on experience with a deep learning framework such as PyTorch.
- Experience designing reward functions, tuning hyperparameters, and implementing exploration strategies.
- Experience with perception-in-the-loop control using real-time sensory inputs.
- Experience deploying RL policies on real-world bipedal or quadrupedal robots.
Nice to have
- Advanced degree (MS or PhD) in Robotics, Computer Science, or a related field.
- Experience with contact-rich manipulation, policy distillation, or publications in top ML or robotics conferences.
Pay
$187,000 — $292,000 USD (base salary)
Tools
Python, PyTorch, Mujoco-Warp, Isaac
AI focus
Reinforcement learning for humanoid locomotion, whole-body control, and manipulation, with perception integration and sim-to-real deployment.
Model-written summary · the original posting is authoritative