Lumalabs Ai

Research Scientist / Engineer – Reinforcement Learning Infrastructure

Redwood City, USA

Sponsorship not specifiedDetected 1 day ago

KubernetesPyTorchLLMsResearchCommunication

About the role

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.

You will work alongside our research team to design and operate the RL stack for our largest multimodal models.
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
About Luma AI Luma's mission is to build multimodal AI to expand human imagination and capabilities.

Reinforcement learning is how our foundation models go from capable to useful - learning to reason, use tools, and act over long horizons.

To go beyond language models and build more aware, capable and useful systems, the next step function change will come from vision.
About the Role Reinforcement learning is how our foundation models go from capable to useful - learning to reason, use tools, and act over long horizons.

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.

This listing is sourced directly from Lumalabs Ai's careers page and normalized into a canonical job model.