Frontier Safety Assessment Researcher

OpenAI, Inc.; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

OpenAI is seeking a Frontier Assurance researcher to build technical foundations for rigorous assessments of frontier AI risks. You will design assessments with external evaluators, enable experiments, and provide data, docs, and context to scrutiny teams.

The role blends research engineering with practical tool-building and close collaboration across safety, research, and security teams. You will design secure assessment environments, run analyses, reproduce external findings, and document

Qualifications

• 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 implement reliable technical solutions from ambiguous requests.
• Judgment in experimental design, identifying confounders, limitations, and gaps in evidence.
• Enjoy working closely with researchers, explaining technical systems, and helping others investigate difficult questions.
• Value independent scrutiny and can support rigorous assessments that challenge internal assumptions.
• Have an understanding of, or strong interest in, frontier AI risks, alignment, and the evaluation of safeguards.

Responsibilities

• Help design assessments with external evaluators and internal teams: identify consequential safety claims to test, define the evidence and methods needed to assess them, and address gaps in coverage.
• Support the technical execution of third-party assessments and embedded audits focused on frontier risks, translating research questions into experiments and evidence.
• Pair with external researchers to provide data, documentation, and context to assess models and safeguards.
• Design and implement secure access to assessment environments with research, engineering, and security teams.
• Conduct experiments and run analyses on evaluators' behalf when direct access is constrained; document choices and ensure reproducibility.
• Build tooling that automates auditing, assessment workflows, and internal assurance work.
• Reproduce external findings, investigate discrepancies, test mitigations, and address unresolved questions.
• Document methods, findings, and limitations clearly for evaluators and decision-makers.

Skills

Software engineering

Research tooling

ML systems experience

Experiment design

Collaboration with researchers

Debug across system boundaries

Independent scrutiny

Frontier AI risk understanding

Tools

Project documentation

Evaluation infrastructure

Data analysis

Job description

OpenAI is seeking a Frontier Assurance researcher to build technical foundations for rigorous assessments of frontier AI risks. You will design assessments with external evaluators, enable experiments, and provide data, docs, and context to scrutiny teams.

The role blends research engineering with practical tool-building and close collaboration across safety, research, and security teams. You will design secure assessment environments, run analyses, reproduce external findings, and document