Bedrock Robotics
2027 Internship Safety Engineer, Agentic Safety Case Assessment
San Francisco, CA · On-site · Internship · Posted Sep 25, 2026
- Education
- Undergraduate or graduate students; no specific degree or field stated.
About the job
Develop and evaluate a formal safety claim for autonomous excavators using Lean, LLM-assisted proving, and fleet data.
What you'll do
- Trace safety claims through hazards, requirements, mitigations, and evidence; formalize one claim and build a Lean checker with a correctness proof.
- Develop fleet-data checks and audit tooling for LLM-assisted proofs, documenting assumptions and toolchain trust.
- Review specifications with Safety, Systems, and Autonomy teams, and document results, limitations, and recommendations.
What they ask for
- Hands-on experience with Lean and mathlib, particularly real analysis or probability.
- Working knowledge of probability and statistics, including distributions, confidence intervals, and tail bounds.
- Familiarity with knowledge graphs or structured document analysis.
- Ability to formalize informal claims and identify assumptions; experience evaluating LLM-generated code or proofs; background in safety-critical robotics, autonomous vehicles, or heavy equipment.
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.
Tools
Lean, mathlib, LLM, Rust, Aeneas, Verus, Kani
AI focus
Explore LLM-assisted proving and evaluate LLM-generated code or proofs; build audit tooling for automated proofs.
Model-written summary · the original posting is authoritative