RL Infrastructure Engineer for Large-Scale Training

Luma; United States; Sur place; USD 195 000 - 395 000; Plein temps

Résumé du poste

Luma is hiring a senior RL systems engineer in the United States to design and scale post-training RL pipelines that couple policy optimization with thousands of inference workers. You will orchestrate trainer, rollout, environment, and reward workloads across GPUs, pushing performance and correctness at frontier scale.

You will work with vLLM, SGLang, and other tooling to build environments, rewards, verifiers, and evaluation harnesses, and you will ship production-grade tooling, monitoring,

Qualifications

• Hands-on experience post-training LLMs with RL at meaningful 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

RL with LLMs

Distributed training

GPU/cluster understanding

Outils

PyTorch

vLLM

SGLang

TRL

Ray

NCCL

MPI

Description du poste

Luma is hiring a senior RL systems engineer in the United States to design and scale post-training RL pipelines that couple policy optimization with thousands of inference workers. You will orchestrate trainer, rollout, environment, and reward workloads across GPUs, pushing performance and correctness at frontier scale.

You will work with vLLM, SGLang, and other tooling to build environments, rewards, verifiers, and evaluation harnesses, and you will ship production-grade tooling, monitoring,