Researcher, Context - Agent Post-Training

📋 Description

• Design and run experiments to scale context compute.
• Own end-to-end post-training stack improvements (RL, data pipelines).
• Build evals and environments to surface failures and guide fixes.
• Partner with Codex and ChatGPT teams to translate signals into model improvements.
• Work on early-training and alignment interventions (data, eval loops).
• Decide which integrations and fixes are ready for major runs.
• Improve large-scale training machinery: velocity, reliability, cost, latency.
• Debug hard failures in shipped or near-shipped models.

🎯 Requirements

• Strong fundamentals in ML, software, systems, or statistics.
• Hands-on with LLMs, RL, RLHF/RLAIF, post-training, evals, graders, synthetic data.
• Experience with production ML systems and tooling for model training.
• Able to work across research, product, infrastructure, data, evals, safety.
• Comfort turning vague problems into concrete experiments and pipelines.
• Clear communication with cross-functional teams.

🎁 Benefits

• Hybrid work with flexible collaboration.
• Work on frontier AI models with impact.
• Learning and growth in ML research and systems.
• Equal opportunity employer with inclusive policies.