Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Claude Code, Codex, Gemini, Cursor and Grok
Connect

Anthropic

Research Scientist Interpretability

Posted Updated

Description

You will develop methods for understanding language models by reverse engineering learned algorithms. You will design experiments, analyze interpretability features and circuits, build experiment and visualization infrastructure, and communicate findings internally and publicly.

Responsibilities

  • Develop methods for understanding language models
  • Design and run experiments in toy scenarios and large models
  • Create and analyze interpretability features and circuits
  • Build infrastructure for experiments and result visualization
  • Communicate results internally and publicly

Requirements

  • Scientific research
  • Interpretability
  • Python
  • Experimentation
  • Neural network
  • Language model
  • Research infrastructure
  • Data visualization

Benefits

  • Equity donation matching
  • Generous vacation
  • Parental leave
  • Flexible working hours

Skills

Apply

See also