Software Engineer, RL Training Infra

📋 Description

• Keep large-scale RL training runs moving by addressing urgent infra problems.
• Debug issues across training systems, inference, orchestration, and distributed infra.
• Solve hard problems at the research/engineering boundary: scale, reliability, latency, cost.
• Improve reliability and efficiency of RL training runs.
• Help researchers with infra-heavy integrations like multi-agent memory.
• Turn recurring operational issues into tools, systems, or abstractions.

🎯 Requirements

• Strong generalist engineer with ML infrastructure experience.
• Experience with RL, inference, scaling, or ML infrastructure.
• Learns quickly and operates across unfamiliar layers.
• Strong debugger with ownership, low ego, and good communication.
• Comfortable in messy, high-ownership environments with tight timelines.
• Thrives in fast-moving settings prioritizing reliability and speed.

🎁 Benefits

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