2027 Internship Safety Engineer, Agentic Safety Case Assessment

The role

You will explore how formal methods and LLM-assisted proving can strengthen safety arguments. You will work at the intersection of formal methods, statistics, and field robotics to formalize safety claims and verify checkers in Lean.

What you will do

• Trace safety claims through hazards, requirements, mitigations, and evidence
• Build an end-to-end demonstration for one claim by implementing a checker in Lean
• Develop checks for assumptions that can be monitored in fleet data
• Build audit tooling for LLM-assisted proving
• Work with Safety, Systems, and Autonomy teams to review formal specifications
• Document results, limitations, and recommendations for adoption

Required qualifications

• Hands-on experience with Lean and mathlib experience, particularly real analysis or probability
• Working knowledge of probability and statistics (distributions, confidence intervals, tail bounds)
• Familiarity with knowledge graphs or structured document analysis
• Ability to translate informal claims into precise specifications and identify their assumptions
• Experience evaluating LLM-generated code or proofs
• Background in autonomous vehicles, heavy equipment, or other safety-critical robotics

Nice to have

• Exposure to safety or assurance-case practice (GSN, UL 4600, ISO 13849, IEC 61508) or runtime verification
• Experience with Rust verification tools (Aeneas, Verus, Kani) or differential/property-based testing
• Familiarity with knowledge graphs or structured document analysis
• Background in autonomous vehicles, heavy equipment, or other safety-critical robotics

Before you apply

• Designed strictly for students (undergraduate or graduate)
• Opportunities for full-time conversion are highly limited

About the company

Bedrock retrofits heavy equipment like excavators to bring autonomy to real job sites. The team includes veterans from Waymo, Segment, and Uber Freight.