RL Systems Engineer - Scale & Post-Training

Luma; Redwood City (CA); Vor Ort; USD 200.000 - 300.000; Vollzeit

Zusammenfassung

Luma is hiring to build and scale reinforcement learning systems that power large-scale models. You will run post-training RL pipelines across thousands of GPUs, crafting environments, reward signals, and verifiers while integrating inference engines like vLLM and SGLang.

You’ll advance throughput, stability, and efficiency, collaborating with researchers to turn ideas into production training and evaluation runs in a fast, scalable, multi-GPU setting.

Qualifikationen

• Hands-on experience post-training LLMs with RL (PPO/GRPO-family, RLHF, RLVR) 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.

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 at scale

Distributed PyTorch

GPU clusters

RL frameworks

Rollout inference

Tools

vLLM

SGLang

NCCL

MPI

Ray

Kubernetes

Jobbeschreibung

Luma is hiring to build and scale reinforcement learning systems that power large-scale models. You will run post-training RL pipelines across thousands of GPUs, crafting environments, reward signals, and verifiers while integrating inference engines like vLLM and SGLang.

You’ll advance throughput, stability, and efficiency, collaborating with researchers to turn ideas into production training and evaluation runs in a fast, scalable, multi-GPU setting.