A deep systems background - load balancing, scheduling, cluster orchestration, autoscaling, cache-coherent distributed state, high-performance networking, or similar - with enough depth to make architectural calls about how a large fleet is coordinated and to evaluate candidates who go to the kernel and framework level. 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.