Distributed RL Infrastructure Scientist

Luma; United Kingdom; Sur place; GBP 120 000 - 180 000; Plein temps

Résumé du poste

Luma is building unified general intelligence and seeks a hands-on RL engineer to design and scale post-training systems for policy optimization, rollout, and reward loops across thousands of GPUs. You’ll work on environments, verifiers, and evaluation tooling to keep the loop fast, stable, and correct.

You'll bring experience with post-training LLMs, distributed PyTorch, and RL frameworks, and contribute to production systems that run at frontier scale.

Qualifications

• Hands-on experience with post-training LLMs using RL (PPO/GRPO-family, RLHF, RLVR) at meaningful scale.
• Extensive distributed PyTorch training and parallelism (FSDP, Tensor/Pipeline/Expert) for foundation models.
• Experience building RL environments, reward functions, verifiers, or evaluation harnesses for LLM agents.

Responsabilités

• Design, build, and scale distributed RL post-training systems, orchestrating trainer, rollout, environment, and reward workloads across thousands of GPUs.
• Build high-throughput rollout generation, integrating inference engines (vLLM, SGLang), weight synchronization, and asynchronous/off-policy schemes.
• Design RL environments for agentic, multi-step tasks — sandboxed code execution, tool use, computer use, multimodal interaction — reproducible and scalable to millions of episodes.
• Build reward infrastructure: verifiable/programmatic rewards, reward-model serving, LLM-as-judge pipelines, and defenses against reward hacking.
• Develop the evaluation, monitoring, and debugging tooling that keeps large RL runs stable.
• Advance training efficiency and stability, and turn new post-training ideas into production runs with researchers.

Connaissances

RL for LLMs

Distributed PyTorch

RL frameworks

NCCL/MPI

Rollout engines

Outils

vLLM

SGLang

OpenRLHF

Ray

Kubernetes

MPI/NCCL

Description du poste

Luma is building unified general intelligence and seeks a hands-on RL engineer to design and scale post-training systems for policy optimization, rollout, and reward loops across thousands of GPUs. You’ll work on environments, verifiers, and evaluation tooling to keep the loop fast, stable, and correct.

You'll bring experience with post-training LLMs, distributed PyTorch, and RL frameworks, and contribute to production systems that run at frontier scale.