Researcher, Safety - Frontier Assurance
Core
Build technical foundations for rigorous assessments of frontier AI risks, designing experiments and tools for independent safety evaluations.
Role type
Senior IC research engineer (AI safety & auditing)
Builds
Reusable tooling for auditing workflows, evidence collection, and assessment execution for frontier models
Domain
AI safety, alignment, and frontier model evaluation
Deliverable
production ML models
Required skills
software engineering, experimental design, machine learning systems, navigating complex codebases, secure access design, reproducibility, judgment in measurement
Preferred skills
AI safety evaluations, adversarial testing, security research, technical auditing
Technologies
modern machine learning systems, research tools, evaluation infrastructure
Responsibilities
Design assessments with external evaluators to identify safety claims and define evidence methods; Support technical execution of third-party assessments and embedded audits; Provide data and technical context to external researchers; Design and implement secure access to assessment environments; Conduct experiments and analyses on behalf of evaluators when direct access is constrained; Build tooling to automate auditing and assessment workflows; Reproduce external findings and investigate discrepancies; Document methods, findings, and limitations clearly
Seniority
Senior, hands-on IC
