Distributed RL Systems Engineer — Scale Training & Inference

Luma AI; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

Luma AI is building scalable reinforcement learning systems that couple policy optimization with thousands of GPUs, dispatching trainer, rollout, environment, and reward workloads. You will design, build, and scale these post-training systems to run at frontier scale.

The role involves creating high-throughput rollout generation, integrating inference engines like vLLM and SGLang, and developing robust reward and evaluation tooling to keep experiments fast, stable, and correct across large

Qualifications

• Post-training LLMs with RL (PPO/GRPO-family, RLHF, RLVR) at scale.
• Extensive distributed PyTorch training and parallelism 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.

Responsibilities

• 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.

Skills

Post-training RL with LLMs

Distributed PyTorch training

RL environments & verifiers

Rollout inference engines

GPU cluster management

NCCL/MPI networking

Tools

veRL

OpenRLHF

TRL

Ray orchestration

vLLM

SGLang

Job description

Luma AI is building scalable reinforcement learning systems that couple policy optimization with thousands of GPUs, dispatching trainer, rollout, environment, and reward workloads. You will design, build, and scale these post-training systems to run at frontier scale.

The role involves creating high-throughput rollout generation, integrating inference engines like vLLM and SGLang, and developing robust reward and evaluation tooling to keep experiments fast, stable, and correct across large