Research Scientist, Interpretability
Anthropic · San Francisco, CA
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…
Python
This posting is pulled directly from Anthropic's own Greenhouse page and applying happens on their site, not here. Posted 2026-08-21; Skip The Boards re-checks every company's board regularly and removes listings that disappear from the source.