Agent Post-Training, Artifacts Research

Tech Stack

Solid badges = required, outlined = preferred

Responsibilities

• Design and run experiments to improve agentic model behavior for complex software and plugins.
• Own end-to-end improvements to the post-training stack, including RL, data pipelines, graders, reward signals, evals, diagnostics, and model-behavior analysis.
• Build evals and environments to expose model failures, then convert those into training data, product fixes, or new research directions.
• Partner with product teams (Codex, ChatGPT) to translate user needs into model improvements.
• Improve the machinery for large-scale training and launch, focusing on experiment velocity, reliability, observability, reproducibility, cost, latency, and production readiness.

Soft Skills

Culture

Requirements