Senior Applied Scientist: Safe Legged Locomotion (RL)

Amazon Science; Pasadena (CA); On-site; USD 167,000 - 226,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

RSUs

Job summary

Amazon Robotics in Pasadena is seeking an Applied Scientist to own safe legged locomotion algorithms and deploy controllers on physical hardware. You will train policies with RL, perform sim-to-real transfer, and integrate with model-based control for robust, safe gaits across varied terrains.

The role emphasizes collaboration with perception, planning, and safety teams and aims to publish results at top robotics and ML venues. This is a full-time, on-site position in California.

Qualifications

• PhD or master's degree with 6+ years of applied robotics research.
• 3+ years applying RL to physical robotic systems.
• Proven sim-to-real transfer for locomotion or manipulation tasks.
• Strong knowledge of legged robot dynamics and whole-body control fundamentals.
• Proficiency in Python and DL frameworks (PyTorch/JAX) with RL pipelines.
• Experience with physics simulators (Isaac Gym, MuJoCo, PyBullet).
• Publications at top venues (RSS, CoRL, ICRA, NeurIPS, ICLR, IROS).

Responsibilities

• Design, train, and deploy RL policies for dynamic legged locomotion on quadraped and humanoid platforms.
• Collaborate with safety teams to ensure policies stay within safety‑critical bounds.
• Develop sim-to-real transfer pipelines with domain randomization and system identification.
• Integrate learned policies with model‑based whole‑body controllers.
• Formulate reward functions and curricula balancing performance and safety.
• Develop and maintain large‑scale RL training infrastructure and simulators.
• Evaluate policy performance through simulation and hardware experiments.
• Explore advanced techniques like foundation models for control in robotics.

Skills

Reinforcement Learning

Python

Deep Learning

Robotics

Control theory

Education

PhD or Master + 6+ years

Tools

Isaac Gym

MuJoCo

PyBullet

Job description

Amazon Robotics in Pasadena is seeking an Applied Scientist to own safe legged locomotion algorithms and deploy controllers on physical hardware. You will train policies with RL, perform sim-to-real transfer, and integrate with model-based control for robust, safe gaits across varied terrains.

The role emphasizes collaboration with perception, planning, and safety teams and aims to publish results at top robotics and ML venues. This is a full-time, on-site position in California.