AI Interpretability Research Fellow — Mentor-Led, Full-Time

Goodfire; San Francisco (CA); On-site; USD 60,000 - 90,000; Full time

Benefits offered by this job

Competitive compensation

Compute costs covered

Mentorship from MT staff

Co-authored research opportunities

Job summary

Goodfire, an AI interpretability research lab, seeks early-career researchers or engineers to execute a three-month interpretability research project. Fellows will work with leading researchers at Goodfire, receiving structured mentorship and contributing to AI alignment work.

The program emphasizes full-time commitment and rapid, independent execution with mentorship. The role focuses on shipping research, producing a final report, and iterating based on mentor feedback, with opportunities for

Qualifications

• Strong technical background in computer science, machine learning, or related fields.
• Previous machine learning research experience.
• Proficiency in Python and ML frameworks.
• Excellent written and verbal communication skills.

Responsibilities

• Ship research: Execute an assigned interpretability research project.
• Sharpen technical communication: Produce a research report by program completion.
• Iterate fast: Implement feedback from mentors while maintaining independent execution capability.

Skills

Python

ML frameworks

Written communication

Verbal communication

Job description

Goodfire, an AI interpretability research lab, seeks early-career researchers or engineers to execute a three-month interpretability research project. Fellows will work with leading researchers at Goodfire, receiving structured mentorship and contributing to AI alignment work.

The program emphasizes full-time commitment and rapid, independent execution with mentorship. The role focuses on shipping research, producing a final report, and iterating based on mentor feedback, with opportunities for