Applied Scientist, Safe Autonomy & CBF Robotics

Amazon; Pasadena (CA); On-site; USD 143,000 - 193,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

Parental leave

Job summary

Amazon in Pasadena is seeking an Applied Scientist to develop core Control Barrier Function (CBF) algorithms that form the safety foundation of the Compass system for real robots. You will ensure reliable performance under real-world conditions, bridging theory and hardware with safety-certified implementations.

You will push boundaries of CBFs, design invariant sets, hybrid formulations, and backup-set approaches using learned policies and multiple controllers, while collaborating with

Qualifications

• PhD or Master’s degree with 4+ years of experience in deep learning, computer vision, or HRI.
• Deep expertise in Control Barrier Functions with theoretical foundations and practical implementation.
• Strong background in dynamical systems, nonlinear control, formal verification or reachability.
• Proficiency in C++ and Python for real-time control algorithms.
• Publication record at relevant venues (CDC, ACC, ICRA, RSS, Automatica, TAC).

Responsibilities

• Develop and implement novel CBF algorithms with formal safety guarantees while minimizing conservatism.
• Compute and refine invariant sets for high-dimensional robotic systems.
• Design formulations for hybrid dynamical systems with provable safety across mode transitions.
• Address theory-to-practice gaps considering model uncertainty, sensor noise, delays and latency.
• Create reduced- and full-order dynamics models with white-box and black-box approaches.
• Implement real-time optimization solvers within safety-critical control loops.
• Document formal arguments to support third-party safety certification.
• Validate algorithms through simulations and hardware experiments, characterizing failures and safety margins.
• Contribute to theoretical foundations of CBFs and publish in top venues.
• Collaborate with perception, planning, locomotion, and manipulation teams.

Skills

Deep learning

Computer vision

Human-robot interaction

Algorithms implementation

C++

Python

Education

PhD

Master's degree with 4+ years experience

Job description

Amazon in Pasadena is seeking an Applied Scientist to develop core Control Barrier Function (CBF) algorithms that form the safety foundation of the Compass system for real robots. You will ensure reliable performance under real-world conditions, bridging theory and hardware with safety-certified implementations.

You will push boundaries of CBFs, design invariant sets, hybrid formulations, and backup-set approaches using learned policies and multiple controllers, while collaborating with