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
Big Data • Information Technology • Software • Analytics • Energy
Lead go-to-market strategy and execute full-funnel growth marketing campaigns for energy-focused SaaS products. Drive pipeline, product adoption, and customer engagement through cross-functional collaboration with product marketing, sales, digital marketing, and analytics. Analyze performance, optimize programs, support launches and market expansions, and identify new growth opportunities from market and customer insights.
.png)
Cloud • Insurance • Payments • Software • Business Intelligence • App development • Big Data Analytics
The Sr UX Engineer will develop and maintain design systems for insurance software, focusing on user interface design, collaboration with UX teams, and creating scalable components.
Top Skills:
CSSFigmaHTMLJavaScriptReactVue
Artificial Intelligence • Professional Services • Business Intelligence • Consulting • Cybersecurity • Generative AI
Lead Oracle CPQ initiatives and complex projects to drive subscription-based transformations. Implement Oracle CPQ Cloud and Oracle Product Data Hub, design revenue strategies using Zuora Revenue, ensure governance and compliance, improve CX and ICM processes, coach teams, and manage cross-border stakeholder engagements to deliver operational excellence and innovation.
Top Skills:
Incentive Compensation Management (Icm)Oracle Cpq CloudOracle CxOracle Product Data Hub (Pdh)Zuora Revenue
What you need to know about the Montreal Tech Scene
With roots dating back to 1642, Montreal is often recognized for its French-inspired architecture and cobblestone streets lined with traditional shops and cafés. But what truly sets the city apart is how it blends its rich tradition with a modern edge, reflected in its evolving skyline and fast-growing tech industry. According to economic promotion agency Montréal International, the city ranks among the top in North America to invest in artificial intelligence, making it le spot idéal for job seekers who want the best of both worlds.
Key Facts About Montreal Tech
- Number of Tech Workers: 255,000+ (2024, Tourisme Montréal)
- Major Tech Employers: SAP, Google, Microsoft, Cisco
- Key Industries: Artificial intelligence, machine learning, cybersecurity, cloud computing, web development
- Funding Landscape: $1.47 billion in venture capital funding in 2024 (BetaKit)
- Notable Investors: CIBC Innovation Banking, BDC Capital, Investissement Québec, Fonds de solidarité FTQ
- Research Centers and Universities: McGill University, Université de Montréal, Concordia University, Mila Quebec, ÉTS Montréal
