Opportunity type
Training program
Cause areas
AI safety & policy
Routes to impact
Skill-building & building career capital
Learning about important cause areas
Testing your fit for a certain career path
Relevant aptitudes
Conceptual & empirical research
Deadline
2025-08-29
Location
Remote
Description
Neel Nanda is seeking applicants for a paid mechanistic interpretability research program, offering mentorship and hands-on experience in AI safety research.
- Applicants complete a 12–20 hour research task and submit a write-up and executive summary by August 29.
- Top ~32 candidates join a 5-week paid online exploration phase (Sept 29–Oct 31), with the best ~8 advancing to a 12-week in-person research phase in Berkeley (Jan 5–Mar 27).
- All backgrounds and experience levels are welcome; past scholars range from undergraduates to experienced researchers.
- Participants receive mentorship, stipends, and often publish co-first author papers at top ML venues; housing support is provided for the in-person phase.
No specific visa requirements are mentioned in the source.
This text was generated by AI. If you notice any inconsistencies, please let us know using https://airtable.com/appngKrXQ99QHsAo4/shrrnPHkHnhTQNA4u
Join 60k subscribers and sign up for the EA Newsletter, a monthly email with the latest ideas and opportunities