Postdoctoral Scholar - SAF Lab, Compass

Job Summary

Postdoctoral Scholar role in the Safe Autonomy Frontiers (SAF) Lab at Amazon, focusing on control barrier functions (CBFs) and safe autonomy for dynamic robots. Work with the inventor of CBFs, collaborate with top scientists, develop theory, perform experiments, and contribute to Amazon's scientific reputation.

• Push the fundamentals of safe autonomy across theory, learning integration, and perception-based synthesis.
• Develop simulation and evaluation pipelines for large‑scale validation.
• Create sim‑to‑real transfer pipelines enabling hardware deployment.
• Deploy methods on dynamically stable robots, validate science in practice and identify gaps.
• Publish results at top robotics, control, and ML venues.
• Collaborate with product teams and science leaders to set a science roadmap with real robot impact.
• Adhere to safety and professional standards in a high‑stress environment.

• PhD in Computer Science, Robotics, Control, Mechanical Engineering, Electrical Engineering, or a related field with focus on control, learning, and/or robotics.
• Deep understanding of safety‑critical control, including CBFs and safety filters.
• Proficiency in C++ and Python and experience implementing control algorithms or learning policies.
• Experience with robotics physics simulators (Isaac Gym/Sim, Mu Jo Co , PyBullet).
• Experience validating on physical robotic hardware.
• Track record of publications at top‑tier venues such as RSS, ICRA, IROS, CDC, CoRL, NeurIPS, ICLR, L‑CSS, RAL, TRO, TAC.

• Understanding of locomotion, reduced‑order models, layered control architectures, nonlinear control, reachability methods, and whole‑body control.
• Knowledge of learning‑based approaches to robotics (reinforcement learning, diffusion, VLMs, world models).
• Exposure to learning‑based CBF synthesis (neural CBFs, data‑driven barrier functions) and CBF‑RL integration.
• Familiarity with Hamilton‑Jacobi reachability analysis and its relationship to CBF‑based approaches.
• Knowledge of safety‑constrained reinforcement learning (constrained MDPs, Lagrangian methods, shielding, CBF‑based policy filtering).
• Experience with model‑based control (MPC, whole‑body QP controllers, operational‑space control) and/or simulation‑based predictive control (MPPI).
• Experience with hierarchical RL, skill composition, distillation, and multi‑task policy architectures for locomotion.
• Familiarity with real‑time deployment constraints (latency budgets, onboard compute limitations, control‑loop frequencies).
• Experience building or contributing to large‑scale RL training infrastructure (distributed training, GPU clusters).
• Strong communication skills and ability to work across disciplinary boundaries.

Base salary range is $136,000–$184,000 annually. Amazon offers sign‑on payments, restricted stock units (RSUs), and a comprehensive benefits package including medical, dental, vision, prescription, life insurance, EAP, mental health support, flexible spending accounts, adoption and surrogacy reimbursement, 401(k) matching, paid time off, and parental leave. For more information, visit (Use the "Apply for this Job" box below)..

Amazon is an equal‑opportunity employer and does not discriminate on the basis of veteran status, disability, or other legally protected status.