World Models Research Scientist - Controllable Embodied AI

lumalabs-ai; San Francisco (CA); On-site; USD 250,000 - 450,000; Full time

Job summary

Luma is seeking a Research Scientist for the World Models team in San Francisco to push the next generation of generative models into interactive, physically faithful worlds.

You will invent world model architectures, develop controllability mechanisms, define evaluation metrics, run scaling studies, and contribute to open-source releases to support embodied reasoning in real environments.

Qualifications

• PhD or equivalent research record in ML, computer vision, robotics, or related fields.
• Deep expertise in at least one: large-scale generative modeling (video/3D/world), self-supervised representation learning, model-based RL.
• Strong PyTorch and large-scale training experience — you've trained models that hit the limits of a multi-node cluster.
• A research record the field knows (top-venue publications and/or widely-used open releases).

Responsibilities

• Invent next-generation world model architectures — diffusion, transformer, autoregressive, or hybrid — with a particular focus on controllability and physical consistency.
• Develop controllability mechanisms that let an agent step into the world: action conditioning, view conditioning, long-horizon rollouts.
• Define and own the metrics: physical fidelity, long-horizon coherence, action-following, and downstream usefulness for policy training.
• Run scaling studies that tell us where compute, data, and architecture pay off.
• Publish at the frontier; contribute to the open-source release that is the long-term deliverable.

Skills

Large-scale generative modeling

Self-supervised representation学习

Model-based RL

PyTorch

Multi-node training

Education

PhD or equivalent

Tools

PyTorch

Job description

Luma is seeking a Research Scientist for the World Models team in San Francisco to push the next generation of generative models into interactive, physically faithful worlds.

You will invent world model architectures, develop controllability mechanisms, define evaluation metrics, run scaling studies, and contribute to open-source releases to support embodied reasoning in real environments.