Software Engineer, RL Training Infra

Details

The Post-Training Frontiers team trains the frontier agents OpenAI ships to the world through large-scale reinforcement learning. The team works across execution and science, reinforcement learning scaling, research improvements, and engineering infrastructure and internal tools.

This role focuses on keeping frontier reinforcement learning training runs fast, reliable, and unblocked. The engineer will work across scaling and orchestration issues, inference bottlenecks, numerical problems, hardware failures, and large horizontal integrations such as multi-agent capabilities and memory. The role suits a strong generalist who learns quickly, debugs deeply, and is motivated by solving the highest-impact problem in front of the team.

Responsibilities

• Keep large-scale asynchronous reinforcement learning training runs moving by addressing urgent engineering and infrastructure problems.
• Debug issues across training systems, inference, orchestration, scaling, and distributed infrastructure.
• Improve the reliability and efficiency of reinforcement learning training runs.
• Support researchers developing infrastructure-heavy integrations, including multi-agent capabilities and memory.
• Turn recurring operational issues into better tools, systems, processes, automations, or abstractions.
• Work closely with research, infrastructure, and partner teams during tight model-run timelines.
• Become useful quickly in ambiguous areas where ownership matters more than a perfectly scoped project.
• Debug hard failures in shipped or near-shipped models and turn qualitative behavior into concrete hypotheses, experiments, and fixes.

Requirements

• Strong generalist engineering skills with experience in some layer of machine learning infrastructure.
• Ability to learn quickly and operate across unfamiliar technical layers.
• High independence, ownership, attention to detail, and strong debugging skills.
• Experience with reinforcement learning, inference, scaling, training systems, orchestration, or adjacent infrastructure.
• Excellent communication skills and a low-ego, collaborative approach.
• Ability to work in messy areas with tight timelines and prioritize effectively.
• Comfort collaborating with multiple research and product teams.
• Proactive approach to fixing important issues and automating repetitive work.

Nice to Have

• Experience supporting large-scale model training, asynchronous reinforcement learning systems, or high-throughput machine learning infrastructure.
• Experience debugging distributed systems across GPUs, networking, orchestration, or inference stacks.
• Background in performance optimization, scaling, or production-critical infrastructure.
• Experience directly supporting researchers or fast-moving model teams.

About OpenAI

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. The company is an equal opportunity employer and provides reasonable accommodations to applicants with disabilities. Background checks are administered in accordance with applicable law.

Benefits

• Medical, dental, and vision insurance, with employer contributions to Health Savings Accounts.
• Pre-tax accounts for health, dependent care, and commuter expenses.
• 401(k) retirement plan with employer match.
• Paid parental, medical, and caregiver leave.
• Paid time off, company holidays, office closures, and paid sick or safe time as required by applicable law.
• Mental health and wellness support.
• Employer-paid basic life and disability coverage.
• Annual learning and development stipend.
• Daily office meals and eligible meal delivery credits.
• Relocation support for eligible employees.
• Equity and performance-related bonuses for eligible employees.