Agent Post-Training, Artifacts Research
Core
Train frontier models to create polished, useful work products (documents, spreadsheets, slide decks, dashboards, reports, analyses) and teach models to move from vague user goals to finished artifacts with strong structure and visual taste.
Role type
Senior IC machine-learning engineer (agent post-training)
Builds
Data, environments, graders, training methods, feedback loops, and RL/eval pipelines for OpenAI's next-generation agents.
Domain
AI research and deployment, specifically frontier agent training and post-training optimization.
Deliverable
production ML models
Required skills
machine learning fundamentals, software engineering, statistics, LLMs, RL, RLHF/RLAIF, post-training, evals, graders, synthetic data, model training, coding agents, tool-using agents, production ML systems
Preferred skills
research taste, engineering execution, product impact focus, cross-functional collaboration, building load-bearing systems, consulting/finance/marketing/operations/data science background
Technologies
RL, data pipelines, graders, reward signals, evals, diagnostics, model-behavior analysis, synthetic data, multi-agent 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 including RL, data pipelines, graders, reward signals, evals, and diagnostics; Build evals and environments to expose model failures and convert them into training data or product fixes; Partner with product teams to translate user needs into model improvements; Work on early-training and alignment interventions including data mixtures, objectives, and synthetic data; Decide which integrations and fixes are ready for major model runs; Improve large-scale training machinery for experiment velocity, reliability, and production readiness; Debug hard failures in shipped models and convert qualitative behavior into concrete hypotheses and fixes
Seniority
Senior, hands-on IC
