Luma AI is building scalable reinforcement learning systems that couple policy optimization with thousands of GPUs, dispatching trainer, rollout, environment, and reward workloads. You will design, build, and scale these post-training systems to run at frontier scale.
The role involves creating high-throughput rollout generation, integrating inference engines like vLLM and SGLang, and developing robust reward and evaluation tooling to keep experiments fast, stable, and correct across large
#J-18808-Ljbffr