Researcher, Safety - Frontier Assurance

Highlights

• Build technical foundations for rigorous assessments of frontier AI risks.
• Design assessments with external evaluators to test consequential safety claims.
• Build tooling to automate auditing, evidence collection, and evaluation workflows.

What they offer

• Equity

Ideal candidate

A research engineer who thrives on rigorous experimentation and collaboration, excited to enable independent scrutiny of frontier AI systems and turn ambiguous safety questions into trustworthy evidence.

Requirements

• Strong software engineering skills and experience building research tools, evaluation infrastructure, or systems for analyzing complex data
• Practical experience working 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 turn ambiguous requests into reliable implementations
• Sound judgment in 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