Lead RL Infra Engineer: Scale Training & Environments

Luma; Greater London; Presencial; GBP 147.000 - 299.000; Jornada completa

Descripción de la vacante

Luma is building unified general intelligence capable of operating in the physical world. We seek an experienced RL at scale engineer to design, build, and scale distributed RL post‑training systems that coordinate trainer, rollout, environment, and reward workloads across thousands of GPUs.

You will own high‑throughput rollout generation, integrate inference engines like vLLM, implement weight synchronization, and support asynchronous/off‑policy schemes while developing agentic environments for

Formación

• Hands-on experience with post‑training LLMs using RL at meaningful scale.
• Experience building RL environments, reward functions, verifiers, or evaluation harnesses for LLM agents.

Responsabilidades

• 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.
• 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.

Conocimientos

RL at scale

PPO/GRPO RL

PyTorch distributed training

vLLM integration

SGLang

NCCL/MPI networking

RLHF experience

GPU clusters

Herramientas

PyTorch

vLLM

SGLang

Ray

OpenRLHF

Descripción del empleo

Luma is building unified general intelligence capable of operating in the physical world. We seek an experienced RL at scale engineer to design, build, and scale distributed RL post‑training systems that coordinate trainer, rollout, environment, and reward workloads across thousands of GPUs.

You will own high‑throughput rollout generation, integrate inference engines like vLLM, implement weight synchronization, and support asynchronous/off‑policy schemes while developing agentic environments for