General World Models Jobs

…will: Conduct research on pretraining world-action foundation model with various world modalities

foundation model Feed-forward Gaussian splatting and reconstruction World foundation model and generation 3D/multi-view

Knowledge and passion for the worlds of open-source models and generative AI research.

diffusion models, flow matching, DiTs, video generation, multimodal models, world models, or related fields.

and video generation (e.g., latent and video diffusion models, diffusion transformers) A solid foundation in generative modeling and deep learning

parallel generation.

…to have: Experience working with Generative World Models (Cosmos, UniSim, sora-style architectures) Experience

…stack with dynamic and diverse worlds.

Integrate foundation models, tokenizers, chat templates, generation configuration, sampling methods, and model-specific features into the serving platform

Model Registry & Artifact Management Registry: Build and operate a first-class model registry —

foundation model, video/Gaussian generation, diffusion policy, multi-modal robot learning VLA post-training, reinforcement learning

Model experimentation: Try new models and investigate their capabilities, limitations, and fit for different tasks.

foundation model Feed-forward Gaussian splatting and reconstruction World foundation model and generation 3D/multi-view

…Do Own and evolve performance models and modeling methodologies for next-generation accelerator and system architectures.

…APIs for chat completions, text generation, streaming, model configuration, tool calling, structured outputs, multimodal