← All roles

Research Scientist, Interpretability

Anthropic· AI Research & Engineering
Apply on company site
San Francisco, CA$350k - $850kfull-timePosted 11mo ago

About the role

Research role focused on mechanistic interpretability of language models, reverse engineering model algorithms, building interpretable circuits, and developing infrastructure and experiments to understand how neural networks compute.

Responsibilities

  • Develop methods for understanding LLMs by reverse engineering algorithms learned in their weights
  • Design and run robust experiments, both quickly in toy scenarios and at scale in large models
  • Create and analyze new interpretability features and circuits to better understand how models work.
  • Build infrastructure for running experiments and visualizing results
  • Work with colleagues to communicate results internally and publicly

Qualifications

  • Strong track record of scientific research (in any field), and some work on Interpretability
  • Enjoy team science – collaborative approach to discovery
  • Comfort with messy experimental science and pioneering work in a developing field
  • View research and engineering as two sides of the same coin, writing code and running experiments as part of the role
  • Ability to articulate motivations and teach others, and to write up results, including null results
  • Familiarity with Python
  • Bachelor’s degree or equivalent combination of education, training, and/or experience in a field relevant to the role

Skills

Required:PythonScientific research

Benefits

  • Competitive compensation and benefits
  • Optional equity donation matching
  • Generous vacation and parental leave
  • Flexible working hours
  • Lovely office space
Last updated Jul 8, 2026. Interested? Apply on the company site.

About Anthropic

building reliable, interpretable, and steerable AI systems

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

ai-infrastructure-and-developmentliquid-ai-recruiting-targetsetter-30setter-30-2026-q1wing-list-2026wing-list-2026-giga-stage

More open roles at Anthropic