Research Scientist
Goodfire AI · San Francisco, CA · San Francisco
CHECKED 2H AGO
Infrastructureonsite$200k–$400k
At a glance
Highlights
- Develop new techniques for understanding and steering large AI models.
- Prototype tools to visualize and manipulate internal model structures.
- Push interpretability science to make AI debuggable like software.
What they offer
- Market competitive salary
- Equity
- Competitive benefits
Ideal candidate
Mission-driven researcher fascinated by how large models think, eager to own fast-moving interpretability bets and turn ideas into usable tools with a small team.
Requirements
- PhD or equivalent experience in ML, computer science, or a quantitative science
- Deep familiarity with large models and passion for understanding how they work
- Fluency in Python and ML frameworks such as PyTorch
- Strong writing and communication skills for explaining complex ideas
- Drive to move quickly and take ownership
- remote policy
- In person 5 days a week with one company-wide remote week per month
Lab profile
About Goodfire AI
AI interpretability research lab building agents and infrastructure to understand, monitor, and align AI models.
What they build
- Interpretability agents
- Interpretability infrastructure
Known for
- AI interpretability research
- Model understanding and monitoring
- AI alignment