As a Reinforcement Learning Infrastructure Engineer, you'll build that infrastructure to support both large-scale research and production RL workloads a genuinely rare kind of systems work.
What You'll Do
Build and scale distributed rollout infrastructure for reinforcement-learning training jobs
Implement setting execution and verifier-integration pipelines
Design efficient trajectory storage and retrieval for training pipelines
Ensure rollout infrastructure scales reliably across many concurrent RL jobs
Collaborate closely with our research team to support current algorithms and environment types as they're developed
What You'll Bring
5+ years of experience in distributed systems or backend infrastructure engineering
Strong distributed-systems fundamentals and hands-on experience with Kubernetes and orchestration frameworks like Ray
Experience with gRPC-based service architectures
Proficiency in Python and Go
Education B.Tech in Computer Science or a related field.
Nice to Have
Direct RL infrastructure experience (rare, and not required)
Experience at a distributed-systems or database company, applied to a recent domain