Frontier Agent Post-Training: Artifacts Engineer

OpenAI; San Francisco (CA); On-site; USD 380,000 - 500,000; Full time

Job summary

OpenAI is seeking an Agent Post-Training, Artifacts Research expert in San Francisco to train frontier models that generate polished artifacts—documents, dashboards, reports, and analyses. You’ll guide the training signal, improve post-training systems, and work with researchers, engineers, and product teams to ship improvements into production tools.

You will own experiments, evals, data pipelines, and model-behavior analysis, turning failures into actionable research directions and product

Qualifications

• Strong technical fundamentals in machine learning, software engineering, systems, statistics, or related fields.
• 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 that 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 that expose the next set of model failures, then turn those failures into training data, product fixes, or new research directions.
• Partner with Codex and ChatGPT product teams to understand what users need and translate product signal into model improvements.
• Work on early-training and alignment interventions, including data mixtures, objectives, synthetic data, and eval loops that shape downstream agent behavior.
• Help decide which integrations, capabilities, and fixes are ready for inclusion in major model runs.
• Improve the machinery for large-scale training and launch: experiment velocity, reliability, observability, reproducibility, cost, latency, and production readiness.
• Take on cross-functional projects that touch model training, product infrastructure, and the production agent harness, such as multi-agent systems or training directly against production-like environments.
• Debug hard failures in shipped or near-shipped models and turn messy qualitative behavior into concrete hypotheses, experiments, and fixes.

Skills

ML fundamentals

Software engineering

Systems

Statistics

Post-training

Evals

Graders

Synthetic data

Model training

Coding agents

Tool-using agents

Production ML systems

Experiment design

Cross-functional collaboration

Communication

Problem solving

Job description

OpenAI is seeking an Agent Post-Training, Artifacts Research expert in San Francisco to train frontier models that generate polished artifacts—documents, dashboards, reports, and analyses. You’ll guide the training signal, improve post-training systems, and work with researchers, engineers, and product teams to ship improvements into production tools.

You will own experiments, evals, data pipelines, and model-behavior analysis, turning failures into actionable research directions and product