Frontier Agent Post-Training Engineer

OpenAI; California (MO); On-site; USD 200,000 - 320,000; Full time

Job summary

OpenAI is seeking a senior contributor for the Agent Post-Training, Artifacts team to train frontier models that produce polished artifacts such as documents, spreadsheets, dashboards, and reports. You will guide models from vague user goals to well-structured outputs with strong domain judgment, focusing on low latency and robust behavior.

You will partner with researchers, engineers, product teams, infrastructure, and safety partners to shape major model runs and ship improvements into

Qualifications

• Strong technical fundamentals in ML, software engineering, systems or statistics.
• Hands-on experience with LLMs, RL, RLHF/RLAIF, post-training, evals, graders, synthetic data, model training, coding agents, tool-using agents, or production ML systems.

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 (RL, data pipelines, graders, reward signals, evals, diagnostics, and model-behavior analysis).
• Build evals and environments that expose new model failures and turn them into data, fixes or new research directions.
• Partner with Codex and ChatGPT teams to translate product signal into model improvements.
• Work on early-training and alignment interventions including data mixtures and eval loops.
• Decide which integrations and fixes are ready for major model runs.
• Improve training/launch machinery: velocity, reliability, observability, reproducibility, cost, latency, production readiness.
• Lead cross-functional projects across training, product infra, and production harness.

Skills

ML fundamentals

Software engineering

Systems

Statistics

Education

Bachelor's degree in a related field

Tools

RLHF/RLAIF

Post-training pipelines

Evaluations (evals)

Graders

Synthetic data

Model training

Coding agents

Tool-using agents

Production ML systems

Job description

OpenAI is seeking a senior contributor for the Agent Post-Training, Artifacts team to train frontier models that produce polished artifacts such as documents, spreadsheets, dashboards, and reports. You will guide models from vague user goals to well-structured outputs with strong domain judgment, focusing on low latency and robust behavior.

You will partner with researchers, engineers, product teams, infrastructure, and safety partners to shape major model runs and ship improvements into