Jobs

Anthropic is seeking an experienced Research Manager for their Interpretability team, though this is an expression of interest as no open positions are currently available. The Interpretability team focuses on mechanistic interpretability to reverse engineer how trained models work, aiming to make advanced AI systems safe. The manager will support a team of expert researchers and engineers, partnering with a research lead to drive project execution, career development, and hiring. This role is critical for meeting ambitious AI safety research goals and requires a strong background in machine learning or AI, with 2-5 years of technical team leadership experience.