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
Automotive • Big Data • Information Technology • Robotics • Software • Transportation • Manufacturing
Develop and operate CI/CD, build, integration, validation, and release workflows for autonomous driving and ADAS software. Lead scalable cross-team technical initiatives, improve pipeline reliability and observability, establish engineering best practices, contribute to designs and code reviews, mentor engineers, and support technical recruiting. The role focuses on enabling safe, high-quality software delivery for Super Cruise and other autonomous driving systems.
Top Skills:
Adaptive AutosarBazelBuildkiteCanClangCmakeCpputestDockerEthernetGccGithub ActionsGoogletestJenkinsLinNvccPythonQccQnx Os
Blockchain • eCommerce • Fintech • Payments • Software • Financial Services • Cryptocurrency
Leads Square’s GTM strategy and operations across acquisition, retention, expansion, and portfolio growth. Partners with Revenue, Finance, Data Science, Marketing, Product, and Engineering leaders on segmentation, coverage models, investment decisions, performance measurement, executive reporting, and cross-functional initiatives. Drives AI-enabled process innovation, CRM and systems improvements, roadmap execution, and operating cadences while mentoring junior team members.
Top Skills:
AICrm SystemsLlmsLookerSalesforceSnowflakeSQLWorkflow Automation
Cloud • Security • Software • Cybersecurity • Automation
Own and improve software documentation, UI text, information architecture, and docs-as-code systems across GitLab product areas. Lead AI-assisted content governance, quality checks, process improvements, documentation tooling, metrics, and cross-functional initiatives. Partner with engineering, product, design, and UX teams, mentor technical writers, improve user experience, and contribute to GitLab’s open-source community in a remote, globally distributed environment.
Top Skills:
AIDevsecopsDocumentation-As-CodeGitLintingLinux ShellOpen-Source Software
What you need to know about the Boston Tech Scene
Boston is a powerhouse for technology innovation thanks to world-class research universities like MIT and Harvard and a robust pipeline of venture capital investment. Host to the first telephone call and one of the first general-purpose computers ever put into use, Boston is now a hub for biotechnology, robotics and artificial intelligence — though it’s also home to several B2B software giants. So it’s no surprise that the city consistently ranks among the greatest startup ecosystems in the world.
Key Facts About Boston Tech
- Number of Tech Workers: 269,000; 9.4% of overall workforce (2024 CompTIA survey)
- Major Tech Employers: Thermo Fisher Scientific, Toast, Klaviyo, HubSpot, DraftKings
- Key Industries: Artificial intelligence, biotechnology, robotics, software, aerospace
- Funding Landscape: $15.7 billion in venture capital funding in 2024 (Pitchbook)
- Notable Investors: Summit Partners, Volition Capital, Bain Capital Ventures, MassVentures, Highland Capital Partners
- Research Centers and Universities: MIT, Harvard University, Boston College, Tufts University, Boston University, Northeastern University, Smithsonian Astrophysical Observatory, National Bureau of Economic Research, Broad Institute, Lowell Center for Space Science & Technology, National Emerging Infectious Diseases Laboratories



