You'll design RL environments and coding tasks, build the reward signals and verifiers that capture what "good code" means, run training experiments on frontier models, diagnose why a model does (or doesn't) get better at a class of software-engineering work, and improve the speed and reliability of the pipelines that make all of that iterate fast. 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.