About Luma AI Lumas mission is to build multimodal AI to expand human imagination and capabilities We believe that multimodality is critical for intelligence To go beyond language models and build more aware capable and useful systems the next step function change will come from vision So we are working on training and scaling up multimodal foundation models for systems that can see and understand show and explain and eventually interact with our world to effect change About the Role Reinforcement learning is how our foundation models go from capable to useful learning to reason use tools and act over long horizons The RL Infrastructure team builds the systems that make this possible at scale highthroughput distributed training that couples policy optimization with large fleets of inference workers environments that expose models to realistic multistep tasks and the reward verification and evaluation systems that turn model behavior into learning signal Unlike pretraining RL at scale is a fullloop systems problem training rollout generation environment execution and reward computation all run concurrently across thousands of GPUs and must stay fast stable and correct together We are looking for engineers and scientists who have lived this problem people who have posttrained LLMs with RL built environments and verifiers from scratch and debugged what happens when an asynchronous rollout pipeline meets a frontierscale training run You will work alongside our research team to design and operate the RL stack for our largest multimodal models Responsibilities Design build and scale distributed RL posttraining systems for large multimodal models orchestrating trainer rollout environment and reward workloads across thousands of GPUs Build and optimize highthroughput rollout generation including efficient integration of inference engines eg vLLM SGLang into the training loop weight synchronization and asynchronous offpolicy training schemes Design and implement RL environments for agentic and multistep tasks sandboxed code execution tool use computer use and multimodal interaction that are reproducible hermetic and scalable to millions of episodes Build reward infrastructure verifiable programmatic rewards reward model serving LLMasjudge pipelines and defenses against reward hacking Develop the evaluation monitoring and debugging tooling needed to keep large RL runs stable diagnose convergence and throughput regressions and understand model behavior midrun Advance RL training efficiency and stability sequence packing for long multiturn trajectories KV cache reuse across rollouts curriculum and task sampling and resource scheduling across heterogeneous traininginference workloads Collaborate closely with researchers to turn new posttraining ideas RLVR agentic RL longhorizon credit assignment selfimprovement loops into productionquality training runs Experience Handson experience posttraining LLMs with reinforcement learning eg PPO GRPOfamily methods RLHF RLVR RL from verifiable rewards at meaningful scale Extensive experience with distributed PyTorch training and parallelization strategies 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 multiturn tool use Deep familiarity with RL posttraining frameworks and their systems tradeoffs eg veRL OpenRLHF TRL Raybased orchestration and inference engines used for rollouts vLLM SGLang Strong understanding of GPU clusters networking and communication libraries NCCL MPI and how they behave under mixed training inference workloads Preferred Experience running RL training across gt100 GPUs including asynchronous or disaggregated trainerrollout architectures Preferred Experience with containerization and orchestration Kubernetes Ray for large environment fleets and sandboxed workloads Preferred Research contributions in RL for LLMs reasoning agents reward modeling or longhorizon tasks or opensource contributions to RL training frameworks
Visit
Careersaas to find millions of new and unfilled roles, including thousands of remote and hybrid positions.
