Researcher, Safety - Frontier Assurance
$380k - $500k • Remote • San Francisco • FullTime
Posted 3h ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
AI Research Engineer
About the job
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, identifying consequential safety claims to test, defining the evidence and methods needed to assess them, and addressing 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, moving 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.
Responsibilities
- Help design assessments with external evaluators and internal teams, identifying safety claims to test, defining evidence and methods, and addressing coverage gaps.
- Support the technical execution of third-party assessments and embedded audits focused on frontier risks, translating research questions into experiments and analyses.
- Pair closely with external researchers to provide data, technical documentation, and context for model and safeguard assessments.
- Design and implement secure access to assessment environments, making relevant models, tools, and information available.
- Conduct experiments and analyses on behalf of evaluators when direct access is constrained, developing methods collaboratively and ensuring reproducibility.
- Build tooling to automate auditing, assessment workflows, and internal assurance work.
- Reproduce external findings, investigate discrepancies, and work with teams to test mitigations and identify unresolved questions.
- Document methods, findings, and limitations clearly for evaluators and decision-makers.
Requirements
- 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 translate ambiguous research requests into reliable technical implementations.
- Sound judgment in experimental design and measurement, including identifying confounders, limitations, and gaps in evidence.
- Enjoyment of close collaboration with researchers, explaining technical systems, and helping others investigate difficult questions.
- Value for independent scrutiny and ability to support rigorous assessments that challenge internal assumptions.
- 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 is relevant.