Research Scientist, Interpretability

We're looking for researchers and engineers to join our Interpretability team at Anthropic, working on mechanistic interpretability of neural networks to make them safe. Responsibilities include developing methods for understanding LLMs, designing and running robust experiments, and creating and analyzing new interpretability features and circuits.

Requirements

• 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

Benefits

• Competitive compensation
• Benefits
• Optional equity donation matching
• Generous vacation
• Generous parental leave
• Flexible working hours