Amazon Pathways Jobs (NOW HIRING)

We are seeking a Research Scientist to join the SAF Lab. In this role, you will develop the core Control Barrier Function (CBF) theory and algorithms that form the mathematical foundation of the universal safety layer. Key to this process is a feedback loop between theory and practice: developing theory that is deployed on next generation robots and using experimental evaluation to drive new theory.

This will enable you to push the boundaries of CBF theory: layered safety filters and trade-offs between robustness and optimality. A key challenge will be to understand the interplay with CBF theory and learned control policies, constructing safety filters that internalize learned policies and utilizing CBFs in learning to internalize safety. You will work with the inventor of control barrier functions and a team contributing directly to the next generation of CBF theory and its practical deployment across Amazon's diverse robot fleet.

Key job responsibilities
Develop and implement novel CBF algorithms that provide formal safety guarantees while minimizing conservatism to maximize the permissible operating envelope highly dynamic robots
Frame safety filtering within complex layered architectures involving learning-based components, including VLAs, RL-based locomotion and whole-body controllers
Design multi-layer CBF based safety filters, including decision making layers, MPC, and real-time nonlinear feedback control elements
Formalize the interplay between models used in the CBF safety filter and the full order dynamics of the robotic systems, establishing formal guarantees even if the full order system dynamics is not known and contains learning-based elements
Understand the role of perception and semantic representations in the synthesis of CBFs, and the interplay between CBFs
Characterize the trade-offs between optimal safety and robustness to sensor noise, perception error, actuator and sensor failure
Address the theory-to-practice gap by developing CBF methods that are robust to model uncertainty, sensor noise, actuation delays, and computational latency
Implement real-time optimization solvers (e.g., QP-based safety filters) that execute within the tight timing budgets of safety-critical control loops
Validate algorithms through rigorous simulation and hardware experiments, characterizing failure modes and quantifying safety margins
Contribute to the theoretical foundations of CBFs through publications at top-tier controls and robotics venues
Collaborate with perception, planning, locomotion, and manipulation teams to ensure CBF formulations accommodate the needs of upstream and downstream systems
Collaborate with product teams and science leaders to set a science roadmap (with eventual impact on real robots)
A day in the life
Amazon offers a full range of benefits that support you and eligible family members, including domestic partners and their children. Benefits can vary by location, the number of regularly scheduled hours you work, length of employment, and job status such as seasonal or temporary employment. The benefits that generally apply to regular, full-time employees include:
1

Medical, Dental, and Vision Coverage
2. Maternity and Parental Leave Options
3. Paid Time Off (PTO)
4.

401(k) Plan
If you are not sure that every qualification on the list above describes you exactly, we'd still love to hear from you. At Amazon, we value people with unique backgrounds, experiences, and skillsets. If you're passionate about this role and want to make an impact on a global scale, please apply!
About the team
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, quadrupeds, and humanoids. 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 Amazon's path to millions of robots operating alongside people.