RL Systems Engineer - Scaled Post-Training Infrastructure

Luma; Greater London; Sur place; GBP 120 000 - 180 000; Plein temps

Résumé du poste

Luma is building reinforcement learning systems at frontier scale in the UK, coupling policy optimization with thousands of inference workers and agentic environments. You will own the full RL loop across training, rollout, environments and rewards, pushing throughput and correctness as models scale.

Ideal candidates have hands-on post-training LLM RL experience, distributed PyTorch expertise, and a track record delivering scalable RL environments and evaluation harnesses for LLM agents.

Qualifications

• Hands-on experience post-training LLMs with RL at scale.
• Extensive distributed PyTorch training and parallelism (FSDP, Tensor/Pipeline/Expert Parallel) for foundation models.
• Experience building RL environments, reward functions, verifiers, or evaluation harnesses for LLM agents, including sandboxed execution and multi-turn tool use.
• Deep familiarity with RL post-training frameworks (veRL, OpenRLHF, TRL, Ray orchestration) and rollout inference engines (vLLM, SGLang).
• Strong understanding of GPU clusters, networking, and communication libraries (NCCL, MPI) under mixed training and inference workloads.

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

Post-training RL

Distributed PyTorch

RL environments

RL frameworks

GPU clusters

Outils

vLLM

SGLang

veRL

OpenRLHF

TRL

Ray

Description du poste

Luma is building reinforcement learning systems at frontier scale in the UK, coupling policy optimization with thousands of inference workers and agentic environments. You will own the full RL loop across training, rollout, environments and rewards, pushing throughput and correctness as models scale.

Ideal candidates have hands-on post-training LLM RL experience, distributed PyTorch expertise, and a track record delivering scalable RL environments and evaluation harnesses for LLM agents.