Senior Applied Scientist: Safe Legged Locomotion

Amazon; Pasadena, Northern (CA, KY); Hybrid; USD 167,000 - 226,000; Full time

Job summary

Amazon Robotics, Compass Team seeks an Applied Scientist to develop safe legged locomotion algorithms and deploy them on physical hardware. You will train learning-based controllers for quadrupeds and humanoids to walk, run, and recover from disturbances with robustness and safety.

This role blends RL, sim-to-real transfer, and model-based control to form whole-body policies. You will collaborate with perception, planning, and safety teams to close the loop from sensing to action and contribute

Qualifications

• PhD or master's with 6+ years applied research in robotics.
• 3+ years applying RL to physical robotic systems.
• Proven sim-to-real transfer experience for locomotion or manipulation.
• Strong understanding of legged robot dynamics, contact mechanics, and whole-body control.

Responsibilities

• Design, train, and deploy RL policies for dynamic legged locomotion on quadruped and humanoid platforms.
• Collaborate with safety team to ensure locomotion policies operate within safety-critical bounds.
• Develop sim-to-real transfer pipelines with domain randomization and system identification.
• Integrate learned locomotion policies with model-based whole-body controllers.
• Publish research at top robotics and ML venues.
• Collaborate with perception and planning teams for terrain-aware locomotion.

Skills

Python programming

Deep learning frameworks

Reinforcement Learning

Robot locomotion

Publications track record

Education

PhD or Masters with 6+ years experience

Tools

Isaac Gym/Sim

MuJoCo

PyBullet

Job description

Amazon Robotics, Compass Team seeks an Applied Scientist to develop safe legged locomotion algorithms and deploy them on physical hardware. You will train learning-based controllers for quadrupeds and humanoids to walk, run, and recover from disturbances with robustness and safety.

This role blends RL, sim-to-real transfer, and model-based control to form whole-body policies. You will collaborate with perception, planning, and safety teams to close the loop from sensing to action and contribute