Research Fellow
Goodfire is a San Francisco AI interpretability research company building Silico, an agent and infrastructure for understanding, debugging, monitoring, and controlling AI models.
Funding history
About Goodfire
Goodfire is a public benefit corporation and AI interpretability research lab. Its current product, Silico, turns research questions into inspectable experiments and reports, supporting model analysis, debugging, guardrails, and interpretability research.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will execute an assigned AI interpretability research project over a fixed-term fellowship expected to span three months. You will work independently while incorporating structured feedback from mentors, produce a research report by the end of the program, and communicate your work clearly. The role requires full-time, in-person work in San Francisco.
Requirements
- Strong technical background in computer science, machine learning, or a related field
- Previous machine learning research experience
- Proficiency in Python and machine learning frameworks
- Excellent written and verbal communication skills
- Valid U.S. work authorization
- Ability to commit to full-time, in-person work
Responsibilities
- Execute an assigned AI interpretability research project
- Produce a research report by program completion
- Implement mentor feedback while maintaining independent execution capability
Benefits
- Full coverage of necessary compute and API costs
- Direct mentorship from a Member of Technical Staff
- Opportunity to co-author published research in some cases