Jobs

Anthropic is seeking a Research Engineer / Scientist for their Alignment Science team to conduct exploratory experimental research on AI safety. This role focuses on understanding and steering the behavior of powerful AI systems, with an emphasis on risks from future systems (ASL-3 or ASL-4). The ideal candidate is both a scientist and an engineer, passionate about making AI helpful, honest, and harmless. Responsibilities include designing and running ML experiments, building tooling, and contributing to research papers, with interviews conducted in Python.