Research Fellow

About Goodfire Goodfire is an AI interpretability research lab. We build interpretability agents and infrastructure to understand, monitor, and align AI models. We believe that AI is the most consequential technology of our time. Yet AI models are trained by trial and error today, with limited understanding of what drives their behavior. Our goal is to advance the research and technology needed to fully understand and align AI so humanity can trust superintelligence. Goodfire is a public benefit corporation founded by researchers who helped pioneer the field of interpretability at OpenAI and Google DeepMind. We are headquartered in San Francisco and have raised over $200M from leading investors including Lightspeed, Menlo, and B Capital. About the role We are seeking talented, early-career researchers or engineers to execute a research project in AI interpretability. Fellows will work alongside leading interpretability researchers at Goodfire, receiving structured mentorship while contributing to important work in AI alignment. The project is expected to span 3 months, with some flexibility based on project progress and mutual agreement.  What you’ll do 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 We strongly prefer research fellows available to work full-time with the team. What you’ll bring Required experience 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 Preferred qualifications Experience with foundation model and/or AI interpretability research Track record of completing structured research projects end-to-end Success profile Excel at executing well-defined research plans Thrive in collaborative environments Can work independently while incorporating structured feedback Demonstrate strong interest in AI interpretability Our values Goodfire is looking for individuals who embody our values and share our deep commitment to making interpretability accessible. We are building a team first and foremost. Put mission and team first All we do is in service of our mission. We trust each other, deeply care about the success of the organization, and choose to put our team above ourselves. Improve constantly We are constantly looking to improve every piece of the business. We proactively critique ourselves and others in a kind and thoughtful way that translates to practical improvements in the organization. We are pragmatic and consistently implement the obvious fixes that work. Take ownership and initiative There are no bystanders here. We proactively identify problems and take full responsibility over getting a strong result. We are self-driven, own our mistakes, and feel deep responsibility over what we’re building. Action today We have a small amount of time to do something incredibly hard and meaningful. The pace and intensity of the organization is high. If we can take action today or tomorrow, we will choose to do it today. What we offer Competitive compensation aligned with experience and qualifications Full coverage of necessary compute and API costs Direct mentorship from a Member of Technical Staff In some cases, an opportunity to co-author published research This is a fixed-term fellowship position. While full-time positions are not guaranteed following the fellowship, exceptional performance during the program may indicate future opportunities at Goodfire. Most importantly, you'll have the opportunity to join a vital mission at an important point in its trajectory - we are developing groundbreaking technology with a world-class team on the critical path to ensuring a safe and beneficial future for humanity. If you want to do your life’s work with us, even if you believe you do not meet every single requirement, apply now. Note: Fellows must have valid U.S. work authorization to participate in the program. We accept candidates on CPT or OPT/STEM OPT who can commit to full-time, in-person work. We do not sponsor new visas as part of standard fellowship admissions. Exceptions may be considered on a case-by-case basis for truly exceptional candidates with unique expertise.