Staff Autonomy Safety Engineer, 1X

• M.S. or higher in Engineering, Computer Science, Robotics, or related field
• 10+ years of experience in AI/ML, robotics, or autonomous systems, with focus on safety-critical systems
• Strong programming skills in Python and familiarity with ML frameworks
• Experience working with real-world deployed learning-based systems
• Deep understanding of:
• ML robustness
• Generalization failures
• Edge cases and failure modes
• Experience analyzing safety risks in human-interacting systems
• Ability to operate at the intersection of AI, systems engineering, and safety

Desirable

• We are hiring a Staff Autonomy Safety Engineer to lead safety assurance for machine learning–driven autonomy systems
• You will ensure that perception, prediction, and decision-making systems operate safely under real-world conditions, degrade gracefully under uncertainty, and remain robust in complex, human-facing environments
• This is a high-impact, deeply technical role focused on advancing AI safety for embodied systems
• You will work at the intersection of autonomy, safety engineering, and real-world deployment, partnering closely with AI, robotics, and security teams
• You will report to the Director of Robot Safety
• Identify and assess AI-specific hazards in end-to-end autonomy systems
• Define and enforce safety constraints for AI-driven robot behavior involving humans, objects, and environments
• Partner with Functional Safety to translate AI risks into system-level requirements and mitigations
• Collaborate with AI teams to build runtime guardrails that validate and constrain AI-generated actions
• Evaluate risks from:
• Dataset bias
• Distribution shift
• Model drift
• Rare and edge-case failure modes
• Work with Cybersecurity to assess risks from:
• Adversarial inputs
• Prompt injection
• Misuse scenarios
• Provide input on residual risk, uncertainty, and confidence levels in AI behavior
• Help define safety strategies for real-world deployment of autonomous systems
• This is a staff-level, hands-on technical role
• We are looking for someone who can deeply analyze AI system behavior, define safety frameworks, and work directly with engineering teams to implement safeguards in production systems
• You are expected to operate with high autonomy, influence cross-functional teams, and contribute directly to the safety of deployed robots
• What Success Looks Like:
• AI systems operate within well-defined safety envelopes
• Safety constraints are enforced in real-time decision-making systems
• Robust mitigations exist for edge cases and failure modes
• AI behavior is measurable, explainable, and auditable from a safety perspective
• Strong collaboration between AI, Safety, and Security teams
• Reduced risk from distribution shifts, adversarial inputs, and unexpected environments