Agent Post-Training & API Engineer for Power Users

OpenAI; California (MO); On-site; USD 150,000 - 230,000; Full time

Job summary

OpenAI is seeking a versatile engineer to advance agentic models for power users and API developers. You will design evals, build production-like training environments, and translate qualitative failures into data-driven improvements.

The role spans research, engineering, and product collaboration to improve tool use, planning, and instruction following in real-world workflows. The position emphasizes end-to-end ownership of model behavior projects, rapid experimentation, and cross-functional

Qualifications

• Strong technical fundamentals in ML, software engineering, systems, statistics, or applied research.
• Hands-on experience with LLMs, post-training, RL/RLHF/RLAIF, evals, graders, synthetic data, coding agents, tool-using agents, API products, or production ML systems.
• Ability to analyze transcripts/evals/api interactions and form concrete hypotheses about model needs.

Responsibilities

• Design and run experiments to improve model behavior in API and power-user workflows, including function calling, tool use, coding, planning, long-horizon execution, factuality, instruction following, error recovery, and calibrated reasoning.
• Build evals, graders, and environments from real developer workflows and convert observed failures into training data and improvements.
• Partner with API and power-users to identify behavior gaps and turn signals into post-training interventions.
• Improve model behavior when composed into systems: use tools reliably, respect developer intent, handle partial failures, ask for clarifications, maintain coherence across tasks.
• Own end-to-end model behavior projects from analysis to data generation, training experiments, eval design, integration, and launch readiness.
• Develop feedback loops using power-user traces and production-like environments to discover next frontier of failures and gaps.
• Help decide which capabilities and fixes are ready for major model runs and production deployment.
• Debug hard failures by tracing between data, evals, training data, outputs, and product context.
• Work on early-training and alignment interventions, including data mixtures, objectives, synthetic data, and eval loops.
• Improve machinery for large-scale training and launch: velocity, reliability, observability, reproducibility, cost, latency, and production readiness.
• Take on cross-functional projects touching model training, product infrastructure, and production agent harness.

Job description

OpenAI is seeking a versatile engineer to advance agentic models for power users and API developers. You will design evals, build production-like training environments, and translate qualitative failures into data-driven improvements.

The role spans research, engineering, and product collaboration to improve tool use, planning, and instruction following in real-world workflows. The position emphasizes end-to-end ownership of model behavior projects, rapid experimentation, and cross-functional