This description is a summary of our understanding of the job description. Click on 'Apply' button to find out more.

Role Description

This role involves exploring and developing AI video generation models with a focus on World Models.

• Explore how to use World Models for understanding, simulations, and generation of sport or eSport matches (e.g., soccer, DOTA).
• Design, develop, and optimize AI video generation models, particularly with autoregressive architectures.
• Develop and implement state-of-the-art algorithms for synthesizing sport matches.
• Be hands-on, versatile, and possess a sense of humor while supporting data recording for AI horse video models.
• Work closely with other teams on large-scale video-action datasets and implement a complex data-cleaning and pre-processing pipeline.
• Define robust validation strategies and implement custom evaluation metrics comparing synthetic vs. real gameplay.
• Stay updated with relevant literature (e.g., CVPR, NeurIPS, ICML, ICCV) and align it with our roadmap.

Qualifications

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

Benefits

• Opportunity to lead a new wave of interactive video content.
• Chance to transform entire industries and reimagine how digital content is created, shared, and experienced.
• Unique opportunity to shape the future of interactive video content.