Fixed-term fellowship
Research Fellow
Goodfire
- San Francisco, United States · On-site
- Artificial Intelligence, Machine Learning and
About
Goodfire is an AI interpretability research lab that builds interpretability agents and infrastructure to understand, monitor and align AI models. Research fellows are early-career researchers or engineers who execute an assigned AI interpretability research project over about three months with structured mentorship from a member of technical staff, producing a research report by the end of the program and, in some cases, co-authoring published research. Necessary compute and API costs are covered.
Requirements
Strong technical background in computer science, machine learning or a related field; previous machine learning research experience; proficiency in Python and ML frameworks; excellent written and verbal communication. Preferred: experience with foundation-model or interpretability research. Fellows need valid U.S. work authorisation (CPT and OPT/STEM OPT accepted) and must commit to full-time, in-person work; new visas are not sponsored as part of standard admissions.
Topics
Source: Goodfire