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
Leads GitLab’s global SMB new-business organization across EMEA and AMER, overseeing regional sales, BDR, and SDR managers. Owns new-logo strategy, pipeline generation, quota and territory planning, forecasting, revenue reporting, hiring, manager development, and cross-functional alignment. The role drives outbound sales motions, develops team performance, analyzes market opportunities, and represents new-business strategy to senior leadership.
Top Skills:
ClariCRMDevsecopsGitlabMarketing AutomationMarketoSalesforce
eCommerce • Healthtech • Kids + Family • Retail • Social Media
Build and scale reliable data pipelines, Snowflake ingestion systems, ML pipelines, monitoring, and data infrastructure for a large e-commerce platform. Design agentic systems that automate pipeline generation, testing, and maintenance while collaborating with analysts, data scientists, analytics engineers, product teams, and ML teams. This senior individual contributor role emphasizes production AI/LLM systems, platform automation, data modeling, and cross-functional delivery.
Top Skills:
Agentic WorkflowsAirflowAmazon Ec2Amazon EksAmazon S3AWSAws LambdaDbtETLLlmsMachine Learning PipelinesMcp ServersPythonRagSnowflake
Big Data • Fintech • Mobile • Payments • Financial Services
Lead the design, development, and technical strategy for high-availability financial services supporting Affirm’s card loan platform. Build scalable APIs, data models, microservices, and event-driven systems; troubleshoot performance and reliability issues; collaborate cross-functionally on loan attribution and lifecycle requirements; and mentor engineers through technical guidance, design reviews, and code reviews.
Top Skills:
AWSDockerEvent-Driven ArchitectureGCPKotlinKubernetesMicroservicesAzureNoSQLPythonRestful ApisSQL
What you need to know about the London Tech Scene
London isn't just a hub for established businesses; it's also a nursery for innovation. Boasting one of the most recognized fintech ecosystems in Europe, attracting billions in investments each year, London's success has made it a go-to destination for startups looking to make their mark. Top U.K. companies like Hoptin, Moneybox and Marshmallow have already made the city their base — yet fintech is just the beginning. From healthtech to renewable energy to cybersecurity and beyond, the city's startups are breaking new ground across a range of industries.
