and our mission to build safe, beneficial AI systems. As a Research Engineer on this team, you'll ensure our frontier models train... or during high-stress incidents Are passionate about the work itself and want to refine your craft as a research engineer Care...
or scaling pretraining architectures (LLMs, diffusion models, multimodal models, etc.) Are comfortable working with training... our commitment to AI safety and fostering a culture of trust and transparency. The Pretraining Safety team's goal is to build safer...
collaborating with Pretraining. Responsibilities: Implement and analyze research experiments, both quickly in toy scenarios... Interpretability team at Anthropic is working to reverse-engineer how trained models work because we believe that a mechanistic...
Interpretability team at Anthropic is working to reverse-engineer how trained models work because we believe that a mechanistic... programs we're trying to "reverse engineer". A few places to learn more about our work and team at a high level...