Goodfire recruits interpretability research scientists, pitches scaling lab staff on AI safety

leedsharkey · x · 2026-09-12

Goodfire posted a job call for Research Scientists (London & SF), arguing there has never been a more pressing time for safety research—especially interpretability—and directly pitching people at scaling labs. Goodfire is a public benefit corporation building AI that can be understood, debugged, and steered like software, with interpretability researchers from OpenAI and DeepMind and over $200M in backing from B Capital, Menlo Ventures, Lightspeed, Eric Schmidt and others. The role spans interpretability mechanisms, high-upside moonshots, and applied research turning findings into usable tools.

Related event: Goodfire Recruits Interpretability Researchers Amid Lab Turmoil(2 posts)→

Original post →

More from Companies & People

Companies & People channel →