Research Scientist, AI Interpretability - SF + Equity

Goodfire; San Francisco, Northern (CA, KY); Hybrid; USD 200,000 - 400,000; Full time

Job summary

Goodfire in San Francisco is seeking a Research Scientist to advance new interpretability techniques for large AI models. You will work with a small, mission-driven team to conduct original research, build practical tools, and push the field forward.

You will contribute to interpretability mechanisms, moonshots, and applied research, with responsibilities including visualizing internal model structures, collaborating with engineering, and sharing work via publications and open-source.

Qualifications

• PhD or equivalent experience in ML, CS, or a quantitative science.
• Deep familiarity with large models and 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.

Responsibilities

• Conduct original research in interpretability and related fields.
• Prototype techniques to visualize and manipulate internal model structures.
• Collaborate with engineering to turn research into production-ready tools.
• Share your work through publications, demos, and open-source contributions.
• Help define and evolve our research direction.

Skills

Python

PyTorch

Writing & communication

Ownership

Education

PhD or equivalent (ML/CS/quantitative science)

Job description

Goodfire in San Francisco is seeking a Research Scientist to advance new interpretability techniques for large AI models. You will work with a small, mission-driven team to conduct original research, build practical tools, and push the field forward.

You will contribute to interpretability mechanisms, moonshots, and applied research, with responsibilities including visualizing internal model structures, collaborating with engineering, and sharing work via publications and open-source.