Job description
Model Evaluation and Threat Research • San Francisco Bay Area
San Francisco Bay Area
$250,000 - $450,000
- In this role, you'll conduct research on AI capabilities, risks and mitigations through benchmarking and alignment assessment.
- Develop and maintain benchmarks and metrics to measure frontier model capabilities on threat-relevant tasks.
- Build research infrastructure and evaluation methods to assess model behaviour under monitoring protocols.
- Create maintainable, scalable systems and lead projects from ideation to delivery.
- Contribute rigorous research science through literature knowledge and problem-solving on open-ended challenges.
Model Evaluation and Threat Research (formerly Alignment Research Center, Evaluations) is a project focused on evaluating the capabilities and alignment of advanced ML models.