Applied Scientist, Safe RL, Robotics, SAF Lab

About the role

We are seeking an Applied Scientist to join the SAF Lab. In this role, you will lead the effort in safe reinforcement learning (RL) including the development of legged locomotion algorithms that internalize safety and are deployable on physical hardware—enabling highly dynamic robots to walk, run, avoid collisions and recover from disturbances with agility and robustness. You will develop RL architectures that interface with physics-based models (for dynamic retargeting and reward shaping), internalize safety constraints in training, sim-to-real transfer and interface with safety filters at run-time. Therefore, your work will sit at the intersection of safety-critical control and learning, and you will collaborate with others in the SAF Lab and Amazon working on perception, planning, whole-body and safety-critical control.

Responsibilities

• Collaborate with product teams and science leaders to set a science roadmap (with eventual impact on real robots).
• Design, train, and deploy reinforcement learning (RL) policies for dynamic legged locomotion including walking, running, stair climbing, and fall recovery on physical robots.
• Develop sim-to-real transfer pipelines that produce policies robust to the reality gap, including domain randomization, system identification, and adaptive strategies.
• Integrate control-based methods with RL, as inputs to the RL (dynamic retargeting and control-guided rewards), in training (internalizing safety constraints in training), and as the RL feeds into safety layers and whole-body control.
• Develop and maintain large-scale training infrastructure for locomotion policy learning, including physics simulation environments, domain randomization and GPU parallelization.
• Investigate the distillation of locomotion policies, integration with whole-body control, foundation models, VLAs, world models, perception and full-stack autonomy.
• Evaluate policy performance rigorously through simulation benchmarks, hardware experiments, and failure-mode analysis.
• Publish research at top-tier robotics and ML venues and contribute to Amazon's scientific reputation in advanced robotics.
• Collaborate with perception and planning teams to enable terrain-aware and goal-conditioned locomotion behaviors.

Qualifications

• Experience in patents or publications at top-tier peer-reviewed conferences or journals
• PhD in Computer Science, Robotics, Mechanical Engineer, Electrical Engineering, or a related field with a focus on reinforcement learning, robot learning, or control
• Experience applying RL to physical robotic systems (beyond simulation-only work), including demonstrated expertise in sim-to-real transfer on dynamically stable robots
• Strong understanding of legged robot dynamics, contact mechanics, and whole-body control fundamentals
• Proficiency in Python and deep learning frameworks (e.g., PyTorch, JAX) with experience building custom RL training pipelines
• Experience with physics simulators for robotics (e.g., Isaac Gym/Sim, MuJoCo, PyBullet)