Job description
Machine Intelligence Research Institute • San Francisco Bay Area
San Francisco Bay Area
$120,000 - $200,000
-
In this role, you'll research and design technical aspects of AI regulations to reduce existential risks from advanced AI.
-
Develop threat models identifying how AI systems could cause harm and propose preventative measures.
-
Evaluate AI models to demonstrate failure modes and limitations in current policy approaches.
-
Prepare briefings for policymakers on technical AI safety concepts and present findings to non-experts.
-
Design improved AI governance frameworks focusing particularly on risks from superintelligent systems.
The Machine Intelligence Research Institute (MIRI) is an organisation working towards an AI pause through policy and communications work. They also do technical AI alignment research.
Applications are handled by the employer.
AI Safety Careers does not process applications directly.