1 month ago
San Jose, CA, USASenior
Base Salary
$200k - $400k/yr
Responsibilities
- Design and implement reinforcement learning algorithms for embodied agents in simulated and real-world environments.
- Train policies using interaction, feedback, and large-scale experience across diverse tasks.
- Develop reward modeling, credit assignment, exploration, online RL, offline RL, and robustness strategies.
- Build scalable RL training systems with distributed rollouts, simulation infrastructure, and experiment management.
- Design evaluation frameworks for policy performance, stability, and generalization.
- Collaborate with pretraining, video, generative, agent, and robot learning teams to integrate RL into the autonomy stack.
Requirements
- Experience developing and applying reinforcement learning algorithms in complex environments.
- Strong understanding of policy optimization, value methods, and model-based reinforcement learning.
- Experience training policies in simulation and/or real-world systems.
- Proficiency in Python and deep learning frameworks such as PyTorch.
- Experience with large-scale experimentation and distributed training systems.
- Strong experimental rigor, learning-system diagnosis, and improvement skills.
- Solid software engineering skills for building scalable and reliable systems.
- Ability to work independently and drive ambiguous, high-impact technical problems.
- Bonus qualifications include experience with robotics, control systems, embodied AI, offline RL, imitation learning, hybrid learning, reward modeling, human-in-the-loop learning, robotics simulation or deployment, leading AI labs, or relevant publications.
Benefits
- Full-time position requiring five days per week of in-office collaboration in San Jose, California.
- Total compensation may include additional components and benefits depending on the specific role.
Categories
ML EngineeringRobotics