RL Infrastructure Engineer - Scale & Post-Training Systems

AItoolnavio; Greater London; Hybrid; GBP 120.000 - 180.000; Vollzeit

Zusammenfassung

Luma is building unified general intelligence that can generate, understand, and operate in the physical world. We seek a senior RL systems engineer to design, build, and scale post-training RL workloads across thousands of GPUs, orchestrating trainer, rollout, environment, and reward components for production-scale runs.

You will own end-to-end tooling for reliable, fast RL loops and collaborate with researchers to turn ideas into robust, scalable implementations.

Qualifikationen

• Hands-on experience with post-training LLM 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.
• 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.

Aufgaben

• 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.

Kenntnisse

RL post-training

Distributed PyTorch

RL environments

RL frameworks

GPU networking

Tools

veRL

OpenRLHF

TRL

Ray orchestration

vLLM

SGLang

Jobbeschreibung

Luma is building unified general intelligence that can generate, understand, and operate in the physical world. We seek a senior RL systems engineer to design, build, and scale post-training RL workloads across thousands of GPUs, orchestrating trainer, rollout, environment, and reward components for production-scale runs.

You will own end-to-end tooling for reliable, fast RL loops and collaborate with researchers to turn ideas into robust, scalable implementations.