Frontier Agent Post-Training: Computer-Use ML

OpenAI; San Francisco (CA); On-site; USD 295,000 - 445,000; Full time

Benefits offered by this job

Competitive salary

Collaborative work environment

Opportunities for impactful projects

Job summary

OpenAI is looking for an Agent Post-Training specialist in San Francisco to enhance models capable of running applications and navigating workflows. This role includes designing experiments, developing training data, and collaborating with product teams.

The ideal candidate has strong foundations in machine learning, experience with LLMs, and is excited by solving open-ended problems. The position offers a competitive salary and a collaborative environment aimed at impactful AI development.

Qualifications

• Strong technical fundamentals in machine learning, software engineering, systems, statistics, or similar.
• Hands-on experience with machine learning models, especially in training and evaluation.
• Experience with RL, RLHF/RLAIF, model training, coding agents, or production ML systems.

Responsibilities

• Design and run experiments that improve model behavior in complex computer use.
• Own end-to-end improvements to the model training stack.
• Partner with product teams to develop user-driven model improvements.

Skills

Machine learning fundamentals

Software engineering

Systems engineering

Robustness and evaluation of models

Education

Degree in a relevant field

Tools

Machine learning libraries

Python

Job description

OpenAI is looking for an Agent Post-Training specialist in San Francisco to enhance models capable of running applications and navigating workflows. This role includes designing experiments, developing training data, and collaborating with product teams.

The ideal candidate has strong foundations in machine learning, experience with LLMs, and is excited by solving open-ended problems. The position offers a competitive salary and a collaborative environment aimed at impactful AI development.