Frontier AI Safety Researcher & Assessments

OpenAI; San Francisco (CA); On-site; USD 380,000 - 500,000; Full time

Job summary

OpenAI is seeking a researcher for Frontier Assurance to build rigorous assessment frameworks for frontier AI risks. You will design evaluations with external evaluators and internal teams, define evidence needs, and ensure reproducible results.

You will work closely with embedded auditors and researchers to translate concepts into experiments and secure, auditable processes. You will help turn independent scrutiny into concrete evidence about model capabilities, safeguards, and remaining risks,

Qualifications

• Strong software engineering skills and experience building tools for research and evaluation.
• Experience designing and running evaluations for modern ML systems.
• Ability to translate research questions into reproducible experiments and artifacts.

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, analyses, and evidence requirements.
• Pair with external researchers to provide data, technical docs, and context to assess models and safeguards; explain system behavior, configurations, and limitations.
• Design and implement secure access to assessment environments with cross-team collaboration to make models, tools, and information available.
• Conduct experiments and run analyses on evaluators’ behalf when direct access is constrained; document decisions and ensure reproducibility.
• Build tooling that automates auditing, assessment workflows, and internal assurance work, including evidence collection and tracking changes across versions.
• Reproduce external findings, investigate discrepancies, and test proposed mitigations with relevant teams.
• Document methods, findings, and limitations clearly for evaluators and decision-makers.

Skills

Software engineering

Research tooling

Evaluation infrastructure

Experiment design

Tools

Python

Job description

OpenAI is seeking a researcher for Frontier Assurance to build rigorous assessment frameworks for frontier AI risks. You will design evaluations with external evaluators and internal teams, define evidence needs, and ensure reproducible results.

You will work closely with embedded auditors and researchers to translate concepts into experiments and secure, auditable processes. You will help turn independent scrutiny into concrete evidence about model capabilities, safeguards, and remaining risks,