Demonstrated experience shaping performance tooling (Workday, Lattice, CultureAmp, or homegrown), including time working with an internal tools or engineering team to guide product decisions, and partnering with People Analytics, with comfort getting into the data yourself. 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.