Research Scientist - World Model
Most applications go out cold — see where you stand first. No sign-up to start.
Don't just apply. Show up ready.
Olive works from this exact posting — no sign-up to start.
At a glance
Requirements
Credentials this posting asks for.
Job overview
Luma AI is hiring a Research Scientist - World Model. The role focuses on turning Luma's generative video models into world models, inventing next‑generation architectures, developing controllability mechanisms, defining metrics, running scaling studies, and publishing research while contributing to open‑source releases.
Key focus areas include Invent next‑generation world‑model architectures focused on controllability and physical consistency, Develop controllability mechanisms such as action conditioning and long‑horizon rollouts, and Define and own metrics for physical fidelity, coherence, action‑following, and downstream usefulness.
Important skills include Reinforcement Learning, Computer Vision, Robotics, Generative Modeling, Model-Based RL, and PyTorch. Preferred (not required): World Models, Generative Video, Neural Simulation, and 4D Scene Representations.
Skills & qualifications
Skills
Qualifications
Full job description
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.
What You'll Own
-
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 release that is the long-term deliverable.
First 90 Days
One way the first 90 could unfold.
-
Days 1–30 — Immerse & Diagnose: Get deep on the current video models and where they fall short as world models.
-
Days 30–60 — Ship & Validate: Prototype a controllability mechanism or architecture change and measure it against physical-fidelity and action-following metrics.
-
Days 60–90 — Scale & Systemize: Run scaling studies and push the most promising direction toward the open release.
What You Bring
-
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).
Nice to Have
-
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.
About Luma: Luma's mission is to build unified general intelligence that can generate, understand, and operate in the physical world. We believe multimodality is critical for intelligence — the next step beyond language models comes from vision. Luma is an equal opportunity employer.
You've read the whole posting — now see how you match it.