This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences. You''ll sit within our Data Infrastructure team, architecting privacy-preserving systems, leading the implementation of privacy-enhancing technologies across our infrastructure, and providing technical leadership on privacy across engineering, research, and product teams.