Job description
Transluce • San Francisco Bay Area
San Francisco Bay Area
$310,000 - $500,000
- In this role, you'll build and extend AI evaluation methods for measuring model behaviors in response to policy and oversight needs.
- Scope, prototype, and run behavioral evaluations addressing emerging policy requirements.
- Execute government contracts designing evaluations assessing harmful model behaviors and risks.
- Design and run privileged-access evaluations and external oversight exercises with frontier labs.
- Adapt behavioral evaluation pipelines with civil society partners and domain experts.
Transluce is a research lab that builds technology for understanding AI systems and steering them in the public interest.