Reinforcement Learning Engineer

As a Reinforcement Learning Engineer, you will be a core contributor to the intelligence and physical capabilities of our humanoid platforms. This role is dedicated to architecting sophisticated neural network topologies and implementing state-of-the-art RL algorithms to achieve world-class performance in whole-body locomanipulation. You will work alongside a multidisciplinary team to develop high-performance policies and optimized training pipelines that allow our robots to move and interact with the world with unprecedented fluidity. Beyond your technical contributions, you will play a key role in maintaining a high-velocity, ego-free engineering culture — sharing insights, participating in rigorous code reviews, and collaborating closely with hardware and controls teams to ensure our collective success on physical hardware.

• Implement and deploy state-of-the-art RL algorithms to achieve ambitious, world-class performance on dynamic locomotion and manipulation tasks with physical hardware.
• Drive the entire development cycle, from prototyping in simulation to robustly transferring and fine-tuning policies on the robot.
• Optimize and scale the RL training pipeline for faster iteration, contributing to core infrastructure for high-throughput simulation and distributed training.
• Develop and refine motion retargeting pipelines to translate human demonstration data (mocap, teleoperation) into robust reference trajectories for reinforcement learning.
• Collaborate closely with the robotics and hardware teams to diagnose system-level issues and co-develop solutions that enable more complex learned behaviors.
• Analyze and present hardware results to guide future technical directions and demonstrate progress on key company objectives.

• Hands-on expertise (3+ years) with common RL frameworks (e.g., PyTorch, JAX) and high-fidelity physics simulators (e.g., MuJoCo, IsaacGym).
• Mastery of Python for rapid prototyping and training, alongside strong proficiency in C++ for developing performant, deployable code.
• Experience building or utilizing large-scale, distributed training pipelines and a strong intuition for their optimization.
• A strong theoretical understanding of modern reinforcement learning, including deep expertise in areas like imitation learning, model-based RL, and sim-to-real transfer techniques.
• A strong intuition for robot dynamics and controls theory, with the ability to apply these principles to guide and constrain learning-based approaches.
• A results-oriented mindset with a passion for seeing complex algorithms work on real-world hardware.

• A PhD degree in Computer Science, Robotics, or a related field, or an MS degree in a similar field with 2+ years industry experience.
• A proven track record of successfully deploying learning-based policies on physical robotic systems, especially legged robots or manipulators.
• Demonstrated experience mentoring or providing technical guidance to other engineers in a team environment.
• A strong publication record in relevant conferences or journals (e.g., CoRL, RSS, ICRA) is a significant plus.

• Prolonged periods of sitting at a desk and working on a computer
• Vision to read printed materials and a computer screen
• Hearing and speech to communicate