Software Engineer, RL Training Infra
Remote • San Francisco • FullTime
Posted 3mo ago
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
AI Infrastructure Engineer
About the job
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.
Responsibilities
- Keep large-scale async RL 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 RL training runs.
- Assist researchers with infrastructure-heavy integrations, such as multi-agent capabilities or memory.
- Convert recurring operational issues into improved tools, systems, processes, automations, or abstractions.
- Collaborate closely with research, infrastructure, and partner teams during critical model-run timelines.
- Become productive quickly in ambiguous areas, prioritizing ownership over project scope.
- Debug complex failures in shipped or near-shipped models, translating qualitative behavior into concrete hypotheses, experiments, and fixes.
Requirements
- Strong generalist engineer with experience in ML infrastructure.
- Ability to learn quickly and operate across unfamiliar technical layers.
- High independence and ability to plan and fix issues autonomously.
- Experience with RL, inference, scaling, training systems, orchestration, or adjacent infrastructure.
- Strong debugging skills with high ownership, low ego, and excellent communication.
- Ability to quickly become useful in complex environments with tight timelines.
- Comfort collaborating with multiple teams across research and product.
- Proactive in fixing important issues encountered.
- Skilled in prioritizing work and applying an 80/20 approach.
- Enjoy helping others and automating repetitive tasks.