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
Artificial Intelligence • Cloud • HR Tech • Information Technology • Productivity • Software • Automation
Leads cybersecurity sales across Canada by developing go-to-market strategy, driving enterprise revenue, recruiting and coaching sales executives, managing territories and quotas, maintaining forecasts, and closing C-level opportunities. The role partners with ServiceNow teams, solution consultants, marketing, professional services, and channel partners to accelerate pipeline, expand customers, and establish the integrated security platform as a market standard.
Top Skills:
ArmisArtificial IntelligenceCRMServicenowVeza
Artificial Intelligence • Healthtech • Machine Learning • Natural Language Processing • Biotech • Pharmaceutical
Manages, monitors, and closes assigned clinical trial sites, ensuring patient safety, protocol compliance, data quality, regulatory adherence, and timely study delivery. Responsibilities include site relationship management, recruitment support, onsite and remote monitoring, adverse event follow-up, investigational product oversight, issue resolution, audit and CAPA support, reporting, and database release. The role also mentors clinical research associates, supports site activation and feasibility activities, and participates in process improvement initiatives.
Artificial Intelligence • Healthtech • Machine Learning • Natural Language Processing • Biotech • Pharmaceutical
Promotes Pfizer oncology products to healthcare providers, institutions, and organized customers. Educates healthcare professionals on appropriate product use, develops strategic account and territory plans, builds relationships with key opinion leaders, assesses customer needs, overcomes access barriers, and generates demand. The role requires strong pharmaceutical or oncology healthcare experience, scientific communication skills, business acumen, digital proficiency, and the ability to collaborate across a matrixed organization.
What you need to know about the Chicago Tech Scene
With vibrant neighborhoods, great food and more affordable housing than either coast, Chicago might be the most liveable major tech hub. It is the birthplace of modern commodities and futures trading, a national hub for logistics and commerce, and home to the American Medical Association and the American Bar Association. This diverse blend of industry influences has helped Chicago emerge as a major player in verticals like fintech, biotechnology, legal tech, e-commerce and logistics technology. It’s also a major hiring center for tech companies on both coasts.
Key Facts About Chicago Tech
- Number of Tech Workers: 245,800; 5.2% of overall workforce (2024 CompTIA survey)
- Major Tech Employers: McDonald’s, John Deere, Boeing, Morningstar
- Key Industries: Artificial intelligence, biotechnology, fintech, software, logistics technology
- Funding Landscape: $2.5 billion in venture capital funding in 2024 (Pitchbook)
- Notable Investors: Pritzker Group Venture Capital, Arch Venture Partners, MATH Venture Partners, Jump Capital, Hyde Park Venture Partners
- Research Centers and Universities: Northwestern University, University of Chicago, University of Illinois Urbana-Champaign, Illinois Institute of Technology, Argonne National Laboratory, Fermi National Accelerator Laboratory
