Software Engineer, RL Training Infra

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 during tight model run timelines.
• Become useful quickly in messy, ambiguous areas where ownership matters more than a perfectly scoped project.
• Debug failures that cut across model behavior, training data, RL systems, evaluation infrastructure, serving systems, and agent harnesses, then turn those failures into hypotheses, fixes, and durable improvements.

You might thrive in this role if you

• Want to train and ship our frontier models and ensure we make agents genuinely useful for developers, enterprises, researchers, and everyday users.
• Are a strong generalist engineer with experience in some layer of ML infrastructure.
• Have worked on RL, inference, scaling, training systems, orchestration, or adjacent ML infrastructure.
• Learn extremely quickly and are comfortable operating across unfamiliar layers.
• Are a strong debugger with high ownership, low ego, and excellent communication.
• Can land in a messy area with tight timelines, become useful quickly, and gradually raise the quality of the whole system.
• Are energized by fast-moving environments where reliability, speed, and judgment matter.
• Like building load-bearing systems and processes when that is what the team needs, even if the work is not glamorous.

Nice to have

• Experience supporting large-scale model training, async RL systems, or high-throughput ML infrastructure.
• Experience debugging distributed systems across GPUs, networking, orchestration, or inference stacks.
• Background in performance optimization, scaling, or production-critical infrastructure.
• Experience working directly with researchers or fast-moving model teams.