Jobs

Anthropic is seeking a Research Engineer for their Interpretability team to reverse-engineer how trained models work, contributing to the safety of advanced AI systems. This role involves building and maintaining specialized inference and training infrastructure, resolving scaling bottlenecks, and designing tools for rapid experimentation. The ideal candidate has 5-10+ years of software development experience, proficiency in Python, and a strong curiosity for unfamiliar domains, with a focus on the societal impacts of AI.