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
Fintech • Financial Services
Conduct manual penetration tests and secure code reviews across web applications, APIs, AWS infrastructure, and AI systems. Develop AI-assisted security tooling, test LLM applications and agentic systems, triage SAST findings, tune security rules, support test-to-production reviews, and communicate risks to engineering teams. The role also helps establish penetration-testing standards for AI-generated software and agent workflows.
Top Skills:
Ai AgentsAWSGoLlm ApplicationsPythonRubySastSecure SdlcTypescript
Big Data • Fintech • Mobile • Payments • Financial Services
Own and deliver highly available, low-latency backend identity systems supporting consumer onboarding, authentication, and verification. Lead quarterly team goals, guide engineers through complex problems, collaborate with product and design stakeholders, improve technical and code quality standards, monitor system availability, support on-call operations, and mentor team members.
Top Skills:
AWSKotlinKubernetesMySQLPython
3 Hours Ago
Artificial Intelligence • Healthtech • Machine Learning • Natural Language Processing • Biotech • Pharmaceutical
Promotes Pfizer pharmaceutical products to healthcare professionals across Manitoba and Saskatchewan, achieving territory sales objectives. Builds relationships with physicians, pharmacists, and specialists; conducts in-person and virtual engagement, congresses, symposia, and continuing medical education programs. Develops territory business plans, collaborates with internal and external partners, reports adverse events and product complaints, and follows company policies, compliance requirements, and data protection standards.
Top Skills:
Microsoft Copilot
What you need to know about the Ottawa Tech Scene
The capital city of Canada and the nation's fourth-largest urban area, Ottawa has proven a rapidly growing global tech hub. With over 1,800 tech companies, many of which are leaders in their sectors, the city's tech talent now makes up more than 13 percent of its total workforce. This growth is driven not only by the big players like UL Solutions and Dropbox, but also by a thriving startup ecosystem, as new businesses emerge to follow in the footsteps of those that came before them.
