Senior RL Systems Engineer

Il y a 2 jours

Eu, Normandie, France Speedrun Talent Network Temps plein 120 000 € - 160 000 € Contrat

Luma is seeking a senior RL systems engineer to design and scale post-training RL pipelines across thousands of GPUs. You will orchestrate trainer, rollout, and environment workloads, integrating inference engines and reward systems to drive robust, efficient learning at frontier scale.

You will build environments for agentic, multi-step tasks, and develop the tooling to monitor, evaluate, and debug large RL runs. Collaboration with researchers is key to turning ideas into production.