OpenAI
Researcher, Safety - Frontier Assurance
$380K–$500K
San Francisco · Full-time · Posted Oct 13, 2026
About the job
Build technical foundations for independent assessments of frontier AI risks by designing evaluations, supporting external auditors, conducting analyses, and developing assessment tooling.
What you'll do
- Design safety assessments and translate research questions into experiments, methods, and evidence requirements.
- Support external evaluators and embedded auditors with technical access, documentation, experiments, and reproducible analyses.
- Build auditing and assessment tools; reproduce findings, investigate discrepancies, and document results and limitations.
What they ask for
- Strong software engineering skills and experience building research tools, evaluation infrastructure, or systems for analyzing complex data.
- Practical experience with modern machine learning systems, including designing experiments, running evaluations, and interpreting results.
- Ability to navigate unfamiliar codebases and infrastructure, debug across system boundaries, and implement ambiguous research requests reliably.
- Sound judgment in experimental design and measurement, including identifying confounders, limitations, and evidence gaps.
Nice to have
- Experience with AI safety evaluations, adversarial testing, security research, or technical auditing.
- Understanding of, or strong interest in, frontier AI risks, alignment, and safeguard evaluation.
Pay
$380K – $500K USD base salary
AI focus
Research and assessment of frontier AI risks, model capabilities, safeguards, and safety evaluations.
Model-written summary · the original posting is authoritative