AI Video Generation
Research Scientist - World Model
Originally published by Luma AI through its ashby careers source. Applications go to the employer's website, and AIMovieJobs is not the hiring employer.
View original listingQuick facts
Role overview
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. Experience using generative models for downstream embodied tasks (planning, control, evaluation). 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. What You'll OwnInvent next-generation world-model architectures (diffusion, transformer, autoregressive, or hybrid), focused on controllability and physical consistency.
Preferred qualifications
- Prior work on world models, model-based RL, generative video, neural simulation, or 4D scene representations.
- Experience using generative models for downstream embodied tasks (planning, control, evaluation).
- Enthusiasm for open-sourcing frontier models.