OpenAI26.06.2026
Agent Post-Training, Connectors Research
Зарплата не указана
Полная занятостьSan Francisco
Обязанности
- 01Teach models how to interface with top professional software using code
- 02Help train agents to use code, APIs, tools, and structured integrations to operate across applications like Slack, Google Workspace, GitHub, Notion, Linear, Salesforce, and other core systems of work
- 03Enable models to take useful actions across a user’s digital context: finding information, updating systems, coordinating work, generating artifacts, and completing multi-step workflows through the tools teams already use
- 04Design and run experiments that improve agentic model behavior for complex software and plugins
- 05Own end-to-end improvements to the post-training stack, including RL, data pipelines, graders, reward signals, evals, diagnostics, and model-behavior analysis
- 06Build evals and environments that expose the next set of model failures, then turn those failures into training data, product fixes, or new research directions
- 07Partner with Codex and ChatGPT product teams to understand what users need and translate product signal into model improvements
- 08Work on early-training and alignment interventions, including data mixtures, objectives, synthetic data, and eval loops that shape downstream agent behavior
- 09Help decide which integrations, capabilities, and fixes are ready for inclusion in major model runs
- 10Improve the machinery for large-scale training and launch: experiment velocity, reliability, observability, reproducibility, cost, latency, and production readiness
- 11Take 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
- 12Debug hard failures in shipped or near-shipped models and turn messy qualitative behavior into concrete hypotheses, experiments, and fixes
Требования
- 01Have strong technical fundamentals in machine learning, software engineering, systems, statistics, or a related field, and can learn quickly across the parts you have not worked in before
- 02Have 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
- 03Are excited by open-ended problems where the path is unclear, the signal is noisy, and the right answer requires both research taste and engineering execution
- 04Care about product impact and model behavior, not just benchmark movement. You have opinions about what makes an agent useful, reliable, honest, tasteful, and easy to work with
- 05Can move from a vague behavioral problem to a concrete experiment: define the hypothesis, build the pipeline, run the model, analyze the result, and decide what to do next
- 06Are comfortable working across research, product, infrastructure, data, evals, and safety boundaries, and can communicate clearly with each group
- 07Like building load-bearing systems and processes when that is what the team needs, even if the work is not glamorous
- 08Want to train and ship the models that make agents genuinely useful for developers, enterprises, researchers, and everyday users