Agent Post-Training, Context Research

📋 Description Design and run experiments to scale compute on context. Own end-to-end post-training stack improvements: RL, data pipelines, graders, signals. Build evals and environments to surface model failures and enable fixes. Partner with Codex and ChatGPT product teams to translate signals into model improvements. Work on early-training and alignment interventions to shape agent behavior. Help decide which integrations and fixes are ready for major model runs. 🎯 Requirements Strong fundamentals in ML, software engineering, systems, or statistics. Hands-on experience with LLMs, RL, RLHF/RLAIF, post-training, evals. Experience with data pipelines, tooling, and production ML systems. Ability to turn problems into experiments: form hypotheses, build pipelines, run analyses. Comfortable across research, product, infrastructure, data, evals, and safety.