Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Tailor your resume to this Research Scientist / Engineer – Reinforcement Learning Infrastructure role.
Rezi rewrites your resume against Luma's job description. Free.
Tailor your resume to this Research Scientist / Engineer – Reinforcement Learning Infrastructure role.
Rezi rewrites your resume against Luma's job description. Free.
Don't guess if your resume is good enough.
See how it scores against the Research Scientist / Engineer – Reinforcement Learning Infrastructure posting at Luma — free, in seconds.
Don't guess if your resume is good enough.
See how it scores against the Research Scientist / Engineer – Reinforcement Learning Infrastructure posting at Luma — free, in seconds.
About the Role
Build systems for large-scale reinforcement learning, integrating policy optimization with inference workers, agentic environments, and reward systems to transform model behavior into learning signals. RL is crucial for making Luma's models useful.
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, computer use, and multimodal interaction, ensuring reproducibility and scalability.
- Build reward infrastructure encompassing verifiable/programmatic rewards, reward-model serving, LLM-as-judge pipelines, and defenses against reward hacking.
- Develop evaluation, monitoring, and debugging tooling to maintain stability in large RL runs.
- Advance training efficiency and stability, and collaborate with researchers to implement new post-training ideas in production runs.
Requirements
- 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.
- Experience running RL training across 100+ GPUs, including asynchronous or disaggregated trainer/rollout architectures.
- Experience with containerization and orchestration (Kubernetes, Ray) for large environment fleets and sandboxed workloads.
- Research contributions in RL for LLMs or open-source contributions to RL training frameworks.
Skills
- Reinforcement Learning
- Distributed Systems
- PyTorch
- FSDP
- Tensor Parallelism
- Pipeline Parallelism
- Expert Parallelism
- LLM Agents
- Sandboxed Execution
- Multi-turn Tool Use
- RL Post-training Frameworks
- vLLM
- SGLang
- GPU Clusters
- Networking
- NCCL
- MPI
- Containerization
- Kubernetes
- Ray
Location
- Remote
Work Type
- Full-time
Experience Level
- Senior
About the Company
- Luma's mission is to build unified general intelligence that can generate, understand, and operate in the physical world.
- We believe multimodality is critical for intelligence — the next step beyond language models comes from vision.
Equal Opportunity
- Luma is an equal opportunity employer.