Postdoctoral Scholar - SAF Lab, Compass

Amazon; Seattle (WA); On-site; USD 142,800 - 193,200; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

Parental leave

Job summary

Amazon is seeking a Postdoctoral Scholar to join the Safe Autonomy Frontiers Lab in Seattle, focusing on safe autonomy for dynamic robots. You will advance scientific contributions and validate safety techniques experimentally on innovative robotic systems.

The role requires a Ph.D. in a relevant field, rich experience with C++/Python, and a robust background in safety-critical robotics. Join a team at the forefront of research and development in safe autonomy.

Qualifications

• PhD in a related field with focus on control and robotics.
• Deep understanding of safety-critical control.
• Proficiency in C++ and Python for control algorithms.

Responsibilities

• Push forward the science of safe autonomy.
• Develop simulation and evaluation pipelines.
• Validate science on hardware and identify research gaps.

Skills

C++

Python

Robotic systems

Control barrier functions

Reinforcement learning

Education

PhD in Computer Science, Robotics, or related field

Tools

Physics simulators (e.g., Isaac Gym, MuJoCo)

Job description

Job ID: 10455363 | Amazon.com Services LLC

Work with the inventor of control barrier functions in the Safe Autonomy Frontiers (SAF) Lab. The first industry research lab in safe autonomy, developing a universal safety layer for the next generation of robotic systems: mobile robots, manipulators, mobile manipulators, and future platforms with dynamic stability. You will push the frontiers of performant safety for highly dynamic robots: CBF theory integrated with perception and learning, evaluated on next-generation robots. Your work will underpin robots operating alongside people at Amazon's unprecedented scale.

We are seeking a Postdoctoral Scholar to join the SAF Lab. In this role, you will perform research around safe autonomy on highly dynamic robots, with a special focus on loco‑manipulation and dynamically stable robots. This includes, but is not limited to, underlying theory of control barrier functions (CBFs) that enables robust and performant safety on hardware, safe reinforcement learning for agile and robust whole‑body control, layered safety filters that interface with learning modules, and the synthesis of CBFs from perception data and semantic information. You will push the boundaries of safe autonomy and validate your discoveries experimentally on the next generation of robotic platforms.

The SAF lab provides a unique opportunity to collaborate with the inventor of CBFs, top scientists and engineers at Amazon developing the next generation of safe autonomy, while also establishing strong connections with top academic research labs. Your research in the SAF lab will lay the foundations of safe learning on complex robots, removing bottlenecks to deployment and enabling them to safely operate around humans.

Key Responsibilities

• Push forward the fundamental science of safe autonomy. This can be from a variety of perspectives: theoretic contributions, integration with learning, or synthesis from perception. Especially valuable are methods that bridge these different domains.
• Develop the simulation and evaluation pipelines needed to run complex and large‑scale validation of methods developed in high‑fidelity simulation environments.
• Develop sim‑to‑real transfer pipelines that enable the deployment of simulation‑based methods (controllers, policies) on hardware.
• Deploy the methods developed on hardware, with a focus on dynamically stable robots. Validate the underlying science developed in practice and identify gaps between the science and practice to drive innovation in research.
• Publish research at top‑tier robotics, control and ML venues and contribute to Amazon's scientific reputation in advanced robotics.
• Collaborate with product teams and science leaders to set a science roadmap (with eventual impact on real robots).

Basic Qualifications

• PhD in Computer Science, Robotics, Control, Mechanical Engineering, Electrical Engineering, or a related field with a focus on control, learning, and/or robotics.
• Deep understanding of safety‑critical control, including control barrier functions and safety filters.
• Proficiency in C++ and Python with experience implementing control algorithms and/or learning policies.
• Experience with physics simulators for robotics (e.g., Isaac Gym/Sim, MuJoCo, PyBullet).
• Experience validating on physical robotic hardware (not simulation-only).
• Track record of publications at top‑tier venues in control and robotics (e.g., RSS, ICRA, IROS, CDC, CoRL, NeurIPS, ICLR, L‑CSS, RAL, TRO, TAC).

Preferred Qualifications

• Understanding of locomotion, reduced order models, layered control architectures, nonlinear control, reachability methods, and whole‑body control.
• Knowledge of learning‑based approaches to robotics (e.g., reinforcement learning, diffusion, VLMs, world models).
• Exposure to learning‑based approaches for CBF synthesis (e.g., neural CBFs, data‑driven barrier functions) and the integration of CBFs into learning (e.g., CBF‑RL).
• Understanding of control systems engineering, with a specific focus on layered architecture used in robotic systems (high level planning, mid‑level trajectory generation and low‑level feedback control).
• Experience with perception on robotic systems (e.g., depth camera and LiDAR based sensing modalities, sensor fusion, semantic tagging).
• Familiarity with Hamilton‑Jacobi reachability analysis and its relationship to CBF‑based approaches.
• Knowledge of safety‑constrained RL (e.g., 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 (ML, controls, mechanical engineering).

Compensation and Benefits

Salary: 142,800.00 – 193,200.00 USD annually (USA, CA, PASADENA). Your Amazon package will include sign‑on payments and restricted stock units (RSUs). Final compensation will be determined based on experience, qualifications, and location. Amazon also offers comprehensive benefits including health insurance, dental insurance, vision insurance, prescription coverage, basic life and AD&D insurance, supplemental life plans, employee assistance program, mental health support, medical advice line, flexible spending accounts, adoption and surrogacy reimbursement coverage, 401(k) matching, paid time off, and parental leave.

Equal Employment Opportunity

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

Los Angeles County applicants: Job duties for this position include working safely and cooperatively with other employees, supervisors, and staff; adhering to standards of excellence despite stressful conditions; communicating effectively and respectfully with employees, supervisors, and staff to ensure exceptional customer service; and following all federal, state, and local laws and Company policies.