You''ll help run Anthropic''s unified audit program: quarterly audits across SOC 2, HIPAA and the ISO 27000 family including ISO 42001, plus the rest of our certifications, working with our audit firms, our GRC Partners, and control owners across the company. 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.