Startups · AI

Research Scientist - World Model

Luma AI · Redwood City, CA · Remote

← All jobs
About Luma AI

Luma AI is the creative AI platform for video generation and image creation. Powered by the world's leading video generation models, Ray and Uni, and creative agents handling end-to-end workflows. Trusted by leading agencies and brands. Try it free. Backed by General Catalyst, a16z and CRV.

About the role

You'll turn Luma's industry-leading generative video models into world models: interactive, controllable, physically faithful, and useful as a substrate for embodied reasoning. This is the role at the center of the thesis.

What they're looking for

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

You'll turn Luma's industry-leading generative video models into world models: interactive, controllable, physically faithful, and useful as a substrate for embodied reasoning. This is the role at the center of the thesis.

You'll invent next-generation world-model architectures and the controllability that lets an agent step into a generated world, and own the metrics that define success. It fits a researcher with deep generative-modeling or model-based-RL expertise who has trained models to the limits of a multi-node cluster. If you want a narrow, well-scoped research problem, this is broader and more open-ended than that.

Invent next-generation world-model architectures (diffusion, transformer, autoregressive, or hybrid), focused on controllability and physical consistency.

Develop controllability mechanisms — action conditioning, view conditioning, long-horizon rollouts — that let an agent step into the world.

Define and own the metrics: physical fidelity, long-horizon coherence, action-following, and downstream usefulness for policy training.

Run scaling studies that show where compute, data, and architecture pay off.

Publish at the frontier and contribute to the open-source...

Read the full posting on Luma AI's site ↗

Research & AI

Build your edge while you search

Free tools for founders and investors, plus VC Unfiltered, our take on startups, venture and the people who build them.