Goodfire
Research Fellow
San Francisco, CA +1 · Full-time · Posted Jan 17, 2025
- Location
- San Francisco, CA
San Francisco, California, United States - Experience
- Early-career researchers or engineers; previous machine learning research experience required. Project expected to span 3 months, with some flexibility.
- Visa sponsorship
- Valid U.S. work authorization is required. CPT or OPT/STEM OPT candidates are accepted if they can commit to full-time, in-person work. New visas are not sponsored as part of standard fellowship admissions; exceptions may be considered case by case for exceptional candidates with unique expertise.
About the job
Execute a three-month AI interpretability research project with mentorship, then produce a research report.
What you'll do
- Execute an assigned interpretability research project.
- Produce a research report by program completion.
- Implement mentor feedback while working independently.
What they ask for
- 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 skills.
Nice to have
- Experience with foundation model and/or AI interpretability research.
- Track record of completing structured research projects end-to-end.
Tools
Python
AI focus
AI interpretability research supporting AI alignment and understanding, monitoring, and alignment of AI models.
Model-written summary · the original posting is authoritative