Research Scientist
Principles of Intelligence (PrincInt)Remote (London, UK / Bay Area, CA preferred)
AI safety & policy
Full-time
AI safety & policy
Full-time
Deadline
2026-11-20
Salary
$125,000–$170,000 USD gross per year
Routes to impact
Direct high impact on an important cause
Description
Lead research on ambitious mechanistic interpretability, developing data models, analyzing learned features, and building synthetic datasets to benchmark interpretability tools.
- Develop tractable data models inspired by statistical physics
- Quantify relationships between data structure and learned features
- Build synthetic datasets to benchmark and improve interpretability tools
- Shape research direction, own projects end to end, and mentor junior researchers and fellows
- Start date: January 2027; visa sponsorship available for London (UK) and Berkeley / Bay Area (US)
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
