OpenAI
AI Research and Deployment
SoftwareEngineer,RLTrainingInfra
Neural analysis suggests this role is
optimal for Mid candidates.
“Software Engineer, RL Training Infra at OpenAI. Skills: RL Training, ML Infrastructure, Distributed Systems, Debugging. Keep large-scale RL training runs moving. Jump into urgent engineering and infrastructure problems”
Industry & Context.
Debug deeply; Solve hard technical problems
What They're Looking For.
Must Have
Generalist engineer with experience in some layer of ML infrastructure, Experience operating across unfamiliar layers, High ownership, Low ego, Excellent communication
Nice to Have
Experience supporting large-scale model training, Experience supporting async RL systems, Experience supporting high-throughput ML infrastructure, Experience debugging distributed systems across GPUs, networking, orchestration, or inference stacks, Background in performance optimization, Background in scaling, Background in production-critical infrastructure, Experience working directly with researchers, Experience working with fast-moving model teams
What You'll Do.
Keep large-scale RL training runs moving
Jump into urgent engineering and infrastructure problems
Debug issues across training systems
Debug issues across inference
Debug issues across orchestration
Debug issues across scaling
Debug issues across distributed infrastructure
Solve hard technical problems
Improve training reliability
Debug distributed systems
Reduce latency and cost
Make new capabilities robust
Improve reliability for RL training runs
Improve efficiency for RL training runs
Help researchers with infra-heavy integrations
Turn recurring operational issues into better tools
Turn recurring operational issues into better systems
Turn recurring operational issues into better processes
Turn recurring operational issues into better abstractions
Debug failures across model behavior
Debug failures across training data
Debug failures across RL systems
Debug failures across evaluation infrastructure
Debug failures across serving systems
Debug failures across agent harnesses
Turn failures into hypotheses
Turn failures into fixes
Turn failures into durable improvements
How You'll Work.
Team & Collaboration
Work closely with research teams; Work closely with infrastructure teams; Work closely with partner teams; Help researchers who are developing infra-heavy integrations
Communication Scope
Excellent communication
Full Job Description
About the Team The Post-Training Frontiers team creates the frontier agents OpenAI ships to the world. We do the reinforcement learning training for the agentic models we ship in Codex, ChatGPT, and the API (from o1 to 5.5). Our role consists of (1) shepherding all integrations that should go into the final RL run and deciding what can make it in, (2) babysitting and scaling the final run, and (3) building the research and infra for horizontal integrations, such as improving function calling, factuality, multi-agent capabilities, memory, calibrated thinking, etc. About the Role This role focuses on keeping our frontier RL training runs fast, reliable, and unblocked. You will work across engineering and infrastructure problems as they emerge, from scaling and orchestration issues to inference bottlenecks, numerical problems, and hardware failures, as well as supporting large horizontal integrations in the big run, like multi-agent capabilities or memory. This is a role for a strong generalist who quickly learns anything needed for the task, has high attention to detail, debugs deeply, and is motivated by fixing the highest-impact problem in front of the team. In this role, you will: - Keep large-scale RL training runs moving by jumping into the most urgent engineering and infrastructure problems. - Debug issues across training systems, inference, orchestration, scaling, and distributed infrastructure. - Solve hard technical problems at the boundary between research and engineering: scaling experiments, improving training reliability, debugging distributed systems, reducing latency and cost, and making new capabilities robust under real workloads. - Improve reliability and efficiency for RL training runs. - Help researchers who are developing infra-heavy integrations, such as multi-agent capabilities or memory. - Turn recurring operational issues into better tools, systems, processes, or abstractions. - Work closely with research, infrastructure, and partner teams dur
Applying for this Software Engineer, RL Training Infra role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
How to Apply on Ashby
- Ashby is a fast modern ATS — most applications take under 3 minutes.
- The resume parser is strong; verify parsed experience dates and job titles.
- Custom screening questions are often scored algorithmically — answer completely.
- Location field affects geo-based screening; use your actual metro area.
ANONYMOUS · UNFILTERED
What do employees actually say about OpenAI?
Real rants from real employees. Read before you apply.