Agent Training Jobs in San Francisco, CA

About the Team The Agent Post-Training team creates the frontier agents OpenAI ships to the world.

Our work spans three areas: Training: Create training methods, environments and data that teach agents to make better decisions in consequential

About the Team The Agent Post-Training team creates the frontier agents OpenAI ships to the world.

Nice to have Experience with agent harnesses and coding agents as subjects of training and evaluation.

…to build the loop from agent behavior to training data, from training data to better models, and from better models

…new task environments to scale training across agentic

The Agent Engine team designs and builds powerful agentic experiences including

Our training environment for agentic models operates at an extremely high scale and has the flexibility to emulate any environment in which an agent might work.

and use, auto-research, and multi-agent collaboration.

…Do Design and run RL training jobs targeting agentic coding capabilities, iterating on recipes and data.

The Agent Engine team designs and builds powerful agentic experiences including

…and improve voice and chat agents before those agents ever reach

…with evals, evolving evalsets and agentic verifiers, post-training models for use cases like model routing, and training task-specific models