Goodfire is seeking to advance AI development through interpretability research and is looking for talented researchers or engineers to execute a research project in AI interpretability.
Requirements
- Strong technical background in computer science, machine learning, or related fields
- Previous machine learning research experience
- Proficiency in Python programming and ML frameworks
- Experience with LLM and/or AI interpretability research
- Track record of completing structured research projects end-to-end
Responsibilities
- Execute an assigned interpretability research project according to established methodology
- Implement feedback from mentors while maintaining independent execution capability
- Produce a co-authored research blog post by program completion
Other
- Commit at least 20 hours per week
- Put mission and team first
- Improve constantly
- Take ownership and initiative
- Action today
- Excellent written and verbal communication skills
- Strong preference for candidates who are available to begin full-time immediately following the fellowship
- At least two years of relevant experience
