Researcher, Safety - Frontier Assurance

Rozgoo; San Francisco (CA); Hybrid; USD 140,000 - 190,000; Full time

Job summary

OpenAI is seeking a Researcher, Safety to advance Frontier Assurance. You will design rigorous assessments of frontier AI risks, collaborate with external evaluators and internal teams, and help translate research questions into experiments, analyses, and evidence requirements.

You will build tools to automate auditing and ensure reproducible results. You will work on designing secure assessment environments and interpreting model behaviors, with a focus on transparency, safety, and rigorous

Qualifications

• Experience designing evaluations for frontier AI risks and safety claims.
• Ability to work with external evaluators and internal teams on rigorous assessments.
• Familiarity with securing assessment environments and reproducible results.

Responsibilities

• Design and implement assessments with external evaluators and internal teams.
• Support third-party evaluations and embedded audits focused on frontier risks.
• Collaborate with external researchers to provide data, documentation, and context for assessments.
• Develop tooling to automate auditing, evidence collection, and evaluation workflows.
• Document methods and results so evaluators can scrutinize evidence and limitations.

Skills

experimental design

machine learning evaluation

assessment automation

debugging complex systems

evaluation infrastructure

secure access controls

reproducible research

safety evaluations

ai safety evaluations

adversarial testing

security research

technical auditing

frontier ai risks

alignment evaluation

Job description

# Researcher, Safety - Frontier AssuranceNewPosted 1 hour agoApply NowLocation: San FranciscoWork mode: On-siteEmployment: Full-timeExperience: Mid-level · 4+ yrs## About the roleAbout the team The Frontier Assurance team strengthens OpenAI’s safety decisions through independent expertise, rigorous assessment, and public transparency. We coordinate external evaluations of frontier models and safeguards, develop approaches such as embedded auditing, and manage the misalignment disclosure process and safeguard testing. Our work helps independent experts scrutinize OpenAI’s safety approach and ensures their findings inform consequential decisions about advanced AI systems. About the role As a researcher on Frontier Assurance, you will build the technical foundations for rigorous assessments of frontier AI risks. You will help design technical 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. You will work closely with external evaluators and embedded auditors, helping them understand the systems they are assessing and access the models, data, and technical information their work requires. Where direct access is not possible, you will conduct experiments and analyses on their behalf, with methods and results they can meaningfully scrutinize. This role combines research engineering, experimental design, and close technical collaboration. You will move between investigating specific safety questions, navigating complex internal systems, and building reusable tools that make assessments more thorough and efficient. Your work will help turn independent scrutiny into concrete evidence about model capabilities, safeguards, and remaining risks. In this role, you will: 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, working with evaluators to translate research questions into experiments, analyses, and evidence requirements. Pair closely with external researchers to provide the data, technical documentation, and context needed to assess models and safeguards. Help them understand relevant system behavior, configurations, and limitations. Design and implement secure access to assessment environments, working with research, engineering, and security teams to make relevant models, tools, and information available. Conduct experiments and run analyses on evaluators’ behalf when direct access is constrained. Develop methods collaboratively, document implementation choices, and make results reproducible and open to challenge. Build tooling that automates auditing, assessment workflows, and internal assurance work, including evidence collection, evaluation execution, and tracking changes across model or safeguard versions. Reproduce external findings, investigate discrepancies with internal results, and work with relevant teams to test proposed mitigations and identify unresolved questions. Document methods, findings, and limitations clearly so that evaluators and internal decision-makers can understand what the evidence establishes and where uncertainty remains. You might thrive in this role if you: Have strong software engineering skills and experience building research tools, evaluation infrastructure, or systems for analyzing complex data. Have practical experience working with modern machine learning systems, including designing experiments, running evaluations, and interpreting results. Can navigate unfamiliar codebases and infrastructure, debug across system boundaries, and turn ambiguous research requests into reliable technical implementations. Bring sound judgment to experimental design and measurement, including 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. Experience with AI safety evaluations, adversarial testing, security research, or technical auditing would be especially relevant. About OpenAI OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products. AI is an extremely powerful tool that must be created with safety and human needs at its core, and to achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity. We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran s## Requirements* strong software engineering skills for research/evaluation tools* practical experience with modern ML systems and evaluations* ability to debug across unfamiliar codebases and infrastructure* sound judgment in experimental design and measurement* ability to collaborate and explain technical systems## Skills* experimental design* machine learning evaluation* assessment automation* debugging complex systems* evaluation infrastructure* secure access controls* reproducible research* safety evaluations* ai safety evaluations* adversarial testing* security research* technical auditing* frontier ai risks* alignment evaluation