# Research Scientist / Engineer – Reinforcement Learning at Luma AI

- Company: Luma AI
- What the company does: Luma AI is the creative AI platform for video generation and image creation. Powered by the world's leading video generation models, Ray and Uni, and creative agents handling end-to-end workflows. Trusted by leading agencies and brands. Try it free. Backed by General Catalyst, a16z and CRV.
- Company website: https://lumalabs.ai/
- Type: Startups (AI role)
- Level: Mid level
- Location: Redwood City, CA
- Work setup: Remote
- Posted: 2026-07-24
- Apply by: 2026-10-08
- Apply: https://jobs.ashbyhq.com/lumaai/90734653-886d-4f6f-8af8-fb130d5400ab
- Page: https://www.1752.vc/careers/jobs/luma-ai-research-scientist-engineer-reinforcement-learning/

## About the role

You'll build the systems that make reinforcement learning work at frontier scale — coupling policy optimization with large fleets of inference workers, agentic environments, and the reward and verification systems that turn model behavior into learning signal. RL is how Luma's models go from capable to useful.

## What they're looking for

- 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

Tags: Research & AI