Research Scientist / Engineer – Reinforcement Learning Infrastructure

About the role

This role involves building the systems that enable reinforcement learning at frontier scale by coupling policy optimization with large fleets of inference workers and agentic environments. You will be responsible for the full-loop systems problem of training, rollout generation, environment execution, and reward computation across thousands of GPUs. The position is designed for someone with deep experience in post-training LLMs with RL and debugging asynchronous rollout pipelines at scale.

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, weight synchronization, and asynchronous/off-policy schemes.
• Design RL environments for agentic, multi-step tasks including sandboxed code execution, tool use, and multimodal interaction.
• Build reward infrastructure including verifiable rewards, reward-model serving, and LLM-as-judge pipelines.
• 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.

Required skills

• Reinforcement Learning
• LLM post-training
• PPO
• GRPO
• RLHF
• RLVR
• PyTorch
• Distributed training
• FSDP
• Tensor Parallelism
• veRL
• OpenRLHF
• TRL
• Ray
• vLLM

Nice to have

• SGLang
• Kubernetes
• NCCL
• MPI

About the Company

Luma's mission is to build unified general intelligence that can generate, understand, and operate in the physical world. The company believes multimodality is critical for intelligence and that the next step beyond language models comes from vision.