At Oddin, we are a diverse group of innovators working to redefine what's possible in generative content. We're moving from passive viewing to active participation, unlocking new creative frontiers across gaming, entertainment, and education. We are looking for an Applied Science Intern to explore and develop AI video generation models, with a focus on World Models for understanding, simulating, and generating sport or eSport matches.

What You'll Do

Explore how to use World Models for understanding, simulations, and generation of sport or eSport matches like soccer or DOTA.
Design, develop, and optimize AI video generation models, with a particular focus on World Models, experimenting with cutting-edge autoregressive architectures.
Develop and implement state-of-the-art algorithms for synthesizing sport matches.
Work closely with other teams on large-scale video-action datasets, designing and implementing a complex data-cleaning and data pre-processing pipeline.
Define robust validation strategies and implement custom evaluation metrics comparing synthetic versus real gameplay.
Stay current with relevant literature from venues like CVPR, NeurIPS, ICML, and ICCV, and help align it with our roadmap.

What We're Looking For

Pursuing a PhD, preferably in the San Francisco area.
Published research at top-tier Computer Vision, AI, or Graphics venues (e.g., CVPR, ICML, ICCV, Siggraph, NeurIPS).
Demonstrated hands-on experience building and running generative Computer Vision models like GANs, DiT, or VAEs.
Solid understanding of neural architectures and paradigms, including Transformers, Denoising Diffusion Models, RNNs, Sequence Models, and CNNs.
Solid understanding of VAEs and concepts like ELBO.
Basic understanding of Reinforcement Learning.
Proficiency in Python and PyTorch.