Research Scientist Engineer Reinforcement Learning
Luma AI develops multimodal creative AI agents, video and image generation models, and an API for generative media workflows.
Funding history
About Luma AI
Luma AI is an active AI company whose Luma Agents product plans, generates, iterates, and refines creative work across video, image, audio, and text. Its first-party materials describe proprietary Ray video and Uni image models, as well as developer API access.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design and scale distributed RL post-training systems across training, rollout, environment, and reward workloads. You will build rollout generation, agent environments, reward infrastructure, evaluation and debugging tools, and improve training efficiency and stability for production research runs.
Requirements
- Experience post-training large language models with reinforcement learning at meaningful scale
- Extensive distributed PyTorch training and foundation-model parallelism experience
- Experience building reinforcement-learning environments, reward functions, verifiers, or evaluation harnesses for LLM agents
- Familiarity with veRL, OpenRLHF, TRL, Ray, vLLM, and SGLang
- Understanding of GPU clusters, networking, NCCL, and MPI
Responsibilities
- Design and scale distributed reinforcement-learning post-training systems
- Build high-throughput rollout generation and inference integrations
- Design scalable reinforcement-learning environments for agentic tasks
- Build reward and verification infrastructure
- Develop evaluation, monitoring, and debugging tools
- Improve training efficiency and stability for production runs