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
.png)
Food • Software
Own ChowNow’s business development function by identifying, evaluating, negotiating, and launching strategic partnerships. Build scalable partner frameworks, source revenue and customer acquisition opportunities, manage partner relationships, evaluate new markets, and align initiatives with sales, product, marketing, finance, legal, and engineering teams. The role requires technical fluency with APIs, commercial modeling, negotiation, and periodic travel to conferences, partner locations, and company headquarters.
Top Skills:
APIsPos Integrations
Artificial Intelligence • Big Data • Healthtech • Information Technology • Machine Learning • Software • Analytics
Provides technical support for production radiology systems affecting patient care. Responsibilities include responding to support calls, managing a 20–30 case ticket backlog, documenting incidents, troubleshooting Windows, network, server, hardware, storage, and Oracle database issues, and coordinating with internal teams to resolve customer cases. The role is Canada-based and includes weekday shifts beginning between 5:00 and 9:30 a.m. PST, plus an on-call rotation.
Top Skills:
Active DirectoryCC#C++Enterprise HardwareLanOracle DatabasesPacsPowershellPythonRisStorage SystemsTcp/IpWanWindowsWindows Command LineWindows ServerWindows Workstations
Blockchain • eCommerce • Fintech • Payments • Software • Financial Services • Cryptocurrency
Lead the technical design and delivery of banking features at Cash App, collaborating across teams, driving architecture improvements, and mentoring engineers.
Top Skills:
AWSDatadogDynamoDBGrpcGuiceHibernateHTTPJavaJettyJSONJunitKafkaKotlinMySQLOkhttpPrometheusProtocol BuffersSignalfx
What you need to know about the Austin Tech Scene
Austin has a diverse and thriving tech ecosystem thanks to home-grown companies like Dell and major campuses for IBM, AMD and Apple. The state’s flagship university, the University of Texas at Austin, is known for its engineering school, and the city is known for its annual South by Southwest tech and media conference. Austin’s tech scene spans many verticals, but it’s particularly known for hardware, including semiconductors, as well as AI, biotechnology and cloud computing. And its food and music scene, low taxes and favorable climate has made the city a destination for tech workers from across the country.
Key Facts About Austin Tech
- Number of Tech Workers: 180,500; 13.7% of overall workforce (2024 CompTIA survey)
- Major Tech Employers: Dell, IBM, AMD, Apple, Alphabet
- Key Industries: Artificial intelligence, hardware, cloud computing, software, healthtech
- Funding Landscape: $4.5 billion in VC funding in 2024 (Pitchbook)
- Notable Investors: Live Oak Ventures, Austin Ventures, Hinge Capital, Gigafund, KdT Ventures, Next Coast Ventures, Silverton Partners
- Research Centers and Universities: University of Texas, Southwestern University, Texas State University, Center for Complex Quantum Systems, Oden Institute for Computational Engineering and Sciences, Texas Advanced Computing Center
