Research Fellow, AI Interpretability

Research Fellow, AI Interpretability

Goodfire
Opportunity type
Fellowship
Cause areas
AI safety & policy
Relevant aptitudes
Software engineering
Location
San Francisco Bay Area
Description
Goodfire is offering a fixed-term Research Fellow opportunity for early-career researchers or engineers to contribute to AI interpretability projects alongside leading experts.
  • Execute a 1-2 month interpretability research project with structured mentorship and the potential pathway to a full-time role
  • Collaborate with top researchers from organizations like OpenAI and DeepMind, and co-author a research blog post
  • Receive competitive compensation, full coverage of compute/API costs, and direct mentorship from technical staff
  • Flexible work options: in-person or remote; strong preference for candidates available to transition to full-time after the fellowship
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