Design, build, and operate large-scale RL post-training systems for multimodal foundation models: distributed training, high-throughput rollout generation, environment and reward infrastructure, evaluation and debugging tooling, and efficiency/stability improvements. Collaborate with researchers to productionize RL methods and run stable RL training across thousands of GPUs.
About Luma AI
About the Role
Responsibilities
Experience
Luma's 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.
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: high-throughput distributed training that couples policy optimization with large fleets of inference workers, environments that expose models to realistic multi-step tasks, and the reward, verification, and evaluation systems that turn model behavior into learning signal.
Unlike pretraining, RL at scale is a full-loop 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 post-trained LLMs with RL, built environments and verifiers from scratch, and debugged what happens when an asynchronous rollout pipeline meets a frontier-scale training run. You will work alongside our research team to design and operate the RL stack for our largest multimodal models.
- Design, build, and scale distributed RL post-training systems for large multimodal models — orchestrating trainer, rollout, environment, and reward workloads across thousands of GPUs
- Build and optimize high-throughput rollout generation, including efficient integration of inference engines (e.g. vLLM, SGLang) into the training loop, weight synchronization, and asynchronous / off-policy training schemes
- Design and implement RL environments for agentic and multi-step 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, LLM-as-judge 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 mid-run
- Advance RL training efficiency and stability: sequence packing for long multi-turn trajectories, KV cache reuse across rollouts, curriculum and task sampling, and resource scheduling across heterogeneous training/inference workloads
- Collaborate closely with researchers to turn new post-training ideas (RLVR, agentic RL, long-horizon credit assignment, self-improvement loops) into production-quality training runs
- Hands-on experience post-training LLMs with reinforcement learning (e.g. PPO / GRPO-family 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 multi-turn tool use
- Deep familiarity with RL post-training frameworks and their systems tradeoffs (e.g. veRL, OpenRLHF, TRL, Ray-based 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 >100 GPUs, including asynchronous or disaggregated trainer/rollout 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 long-horizon tasks — or open-source contributions to RL training frameworks
The base pay range for this role is $187,500 – $395,000 per year.
About LumaLuma’s mission is to build unified general intelligence that can generate, understand, and operate in the physical world.
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.
Similar Jobs
Cloud • Security • Software • Cybersecurity • Automation
Build and lead a globally distributed DevOps engineering team responsible for reliable platform capabilities and repository experiences. Hire, mentor, and develop engineers; guide architecture, security, performance, and maintainability; align delivery with product and design; improve agile workflows and execution; integrate AI-assisted tooling; and support operational health, reliability, and incident management.
Top Skills:
Ai-Assisted Development ToolsDevsecopsDistributed SystemsGitGitlabSoftware Delivery Pipelines
Cloud • Computer Vision • Information Technology • Sales • Security • Cybersecurity
Triage, investigate, and respond to security detections across endpoint, identity, email, network, and cloud environments. Analyze EDR telemetry, logs, forensic artifacts, malware, Microsoft 365 incidents, and network activity to determine compromise scope and recommend remediation. Communicate findings and guidance to customers, improve detection and response processes, and use scripting and AI technologies to streamline investigations. The role requires a 4x10 schedule including one weekend day and is open to US citizens and Green Card holders.
Top Skills:
Active DirectoryBashEdrLinuxmacOSMicrosoft 365Microsoft Entra IdMitre Att&CkOktaPowershellPythonSIEMWindows
Artificial Intelligence • Cloud • Consumer Web • Productivity • Software • App development • Data Privacy
Own regional Sales Operations infrastructure for NAMER, including territory and quota planning, account segmentation, forecasting governance, pipeline inspection, CRM hygiene, executive reporting, and operational cadence. Partner with Sales, Finance, Compensation, Systems, Analytics, and Enablement to improve coverage, forecast accuracy, workflow automation, and sales execution. Support organization design, onboarding, incentive programs, and channel deal registration while applying AI-enabled tools and sound business judgment.
Top Skills:
Analytics ToolsArtificial IntelligenceAutomationCRMSalesforceSQLTableau
What you need to know about the Vancouver Tech Scene
Raincouver, Vancity, The Big Smoke — Vancouver is known by many names, and in recent years, it has gained a reputation as a growing hub for both tech and sustainability. Renowned for its natural beauty, the city has become a magnet for professionals eager to create environmental solutions, and with an emphasis on clean technology, renewable energy and environmental innovation, it's attracted companies across various industries, all working toward a shared goal: advancing clean technology.
