Research Scientist, Interpretability at Anthropic

On-site - San Francisco, CA

Apply
More jobs at Anthropic

The Interpretability team at Anthropic is working to reverse-engineer how trained models work because we believe that a mechanistic understanding is the most robust way to make advanced systems safe. We’re looking for researchers and engineers to join our efforts focused on mechanistic interpretability, which aims to discover how neural network parameters map to meaningful algorithms. The team builds microscopes and reverse-engineering tools, collaborates with other Anthropic research groups, and develops methods to decompose models into interpretable components.

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

Technologies

Transformer circuitsNeural networksHaikuSonnet

See if your resume is ready for this job

See how our AI can optimize your resume and improve your chances for this role.