Join

There is real work to do.

We work with people who take reliability seriously — researchers, engineers, and the institutions deploying AI in the field.

Research Fellow — AI Evaluation

Full-time

Design benchmarks and reliability metrics for high-stakes language-model tasks.

Full-time

Build agentic systems and simulation infrastructure that runs in real operational settings.

PhD / MS

Join a program in evaluation, governance, assurance, or systems as a graduate researcher.

Collaboration

Public-safety institutions interested in evaluating or piloting trustworthy AI.

We're always glad to hear from people who care about this problem. Tell us what you'd want to work on.