Own the scientific validity of frontier preparedness evaluations
Design new evals grounded in real threat models (CBRN, cyber, frontier risks)
Define datasets, graders, rubrics, and threshold guidance
Produce auditable artifacts (evaluation cards, capability reports, system-card inputs)
Build scalable systems to support evaluations
Collaborate with leadership to trust high-stakes launches

🎯 Requirements

Experience in ML research engineering or ML observability
Ability to build evaluations for frontier AI models
Strong data handling: datasets, graders, rubrics, and thresholding
Red-teaming mindset and capability with risk assessment
Excellent cross-functional communication

🎁 Benefits

Equity options and market-competitive salary
OpenAI benefits and growth opportunities

Apply on employer's website

This employer gathers applications via their own applicant tracking system.

You will be redirected to an external application form.

Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.

Activate JobCopilot