Research Intern – Video World Models (Research & ML Systems)
Description
We are seeking an exceptional Research Intern to join our team in building the next generation of video world models. While traditional generative models focus on creating passive video (text-to-video), our mission is to build "World Models"—foundation models that understand physics, causality, and dynamics directly from large-scale data, and can be explored and interacted in real-time. You will work at the frontier of generative AI research, enabling the model to "dream" and interact with complex virtual worlds.
Responsibilities
- Build the next generation of video world models.
- Develop foundation models that understand physics, causality, and dynamics.
- Enable models to "dream" and interact with complex virtual worlds.
Requirements
- Currently pursuing a PhD (or Master’s degree with strong research track record) in Computer Science, Machine Learning, or a related field.
- Strong proficiency in Python and a deep learning framework (PyTorch or JAX). Experience in large-scale machine learning systems is a great plus.
- Deep understanding of Generative Models (Diffusion, Transformers, VAEs, Auto-regressive models).
- Publication Record: First-author publications in top AI venues (CVPR, ICCV, NeurIPS, ICML, ICLR, etc.).
Benefits
- Eligible for 1 hour of paid sick leave for every 30 hours worked and up to 13 paid holidays throughout the calendar year.
- Full-time interns are eligible to enroll in the Company-sponsored medical plan.
