AI Interpretability Researcher - Impact for Safe AI

Goodfire, an AI interpretability lab in San Francisco, seeks candidates with at least two years of relevant experience. The role is based in our SF HQ with in-person work five days a week and one company-wide remote week per month. We offer a market-competitive salary, equity, and comprehensive benefits, and you will work on groundbreaking AI safety and alignment technology with a world-class team. Join us to help design systems that make AI more understandable, controllable, and beneficial for