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 will work closely with partners across Finance, Procurement, Payroll, Legal, Tax, and Finance Systems, and you will help us build a close that scales with the company, with a lot of room to improve how the work gets done as we grow.