Research Scientist, Interpretability

Develop methods for understanding LLMs by reverse engineering the 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. You will thrive if you have a strong research track record, enjoy team science, are comfortable with messy experimental science, and can bridge research and engineering.