Forward Deployed Research Scientist
Goodfire is a San Francisco AI interpretability research company building Silico, an agent and infrastructure for understanding, debugging, monitoring, and controlling AI models.
Funding history
About Goodfire
Goodfire is a public benefit corporation and AI interpretability research lab. Its current product, Silico, turns research questions into inspectable experiments and reports, supporting model analysis, debugging, guardrails, and interpretability research.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will work directly with customers to conduct original interpretability research. You will define problems and hypotheses, source data, build and iterate on tools, prototype techniques for model internals, collaborate on production-ready implementations, and help shape research direction.
Requirements
- MS, PhD, or equivalent computer science experience
- Machine learning background and interpretability experience
- Familiarity with large models
- Python proficiency
- Experience with PyTorch
- Experience leading research in a forward-deployed environment
Responsibilities
- Conduct original interpretability research with customers
- Define research problems and hypotheses
- Source data and build research tools
- Prototype techniques to visualize and manipulate internal model structures
- Collaborate with engineering on production-ready tools
- Drive partnership delivery and help evolve research direction
Benefits
- Equity
- Competitive benefits
- One company-wide remote week per month