Applied Interpretability Scientist for Real-World AI

Goodfire; San Francisco (CA); Hybrid; USD 220,000 - 315,000; Full time

Benefits offered by this job

Equity

Competitive benefits

Hybrid work arrangement

Job summary

Goodfire seeks a Forward Deployed Research Scientist to work directly with customers, applying interpretability to solve novel problems. You will lead research with partners, define hypotheses, source data, build tools, and translate research into real-world applications.

Ideal candidates have MS/PhD in CS, strong ML background, and fluency in Python with PyTorch. You will join a mission-driven team in San Francisco, with a mix of on-site and remote collaboration and the opportunity to shape our

Qualifications

• MS/PhD in CS or equivalent with strong ML background.
• Deep familiarity with large models and interpretability.
• Fluency in Python and ML frameworks such as PyTorch.

Responsibilities

• Work directly with customers to conduct original research in interpretability.
• Prototype techniques to visualize and manipulate internal model structures.
• Collaborate with engineering to turn research into production-ready tools.
• Drive partnership success by collaborating closely with our customers and partners.
• Help define and evolve our research direction.

Skills

ML basics

Python

PyTorch

Communication

Education

MS/PhD in CS

Tools

None

Job description

Goodfire seeks a Forward Deployed Research Scientist to work directly with customers, applying interpretability to solve novel problems. You will lead research with partners, define hypotheses, source data, build tools, and translate research into real-world applications.

Ideal candidates have MS/PhD in CS, strong ML background, and fluency in Python with PyTorch. You will join a mission-driven team in San Francisco, with a mix of on-site and remote collaboration and the opportunity to shape our