Video AI Research Intern: Vision Foundation Models

Lightspeed Studios; Singapore; On-site; SGD 90,000 - 150,000; Full time

Job summary

Lightspeed Tech Center at Lightspeed Studios is pursuing advanced research to design and iterate on next-generation video generation foundations. The role focuses on long-context attention, memory mechanisms, tokenizers, and scaling laws for multi-resolution video. You will lead experiments, define data strategies, and publish results as part of a cutting-edge R&D team developing PUBG Mobile and other top games.

Qualifications

• Pursuing PhD with first-author papers at top-tier conferences.
• Proficient in the principles and engineering of diffusion models and autoregressive generation.
• Experience training video/image generation models from scratch; highly proficient in PyTorch and large-scale distributed training.
• Deep understanding of the design trade-offs in Video VAE/Tokenizers, with 3+ years of relevant research experience.
• Publications related to video generation or diffusion models.
• Experience leading end-to-end video foundation model projects is preferred.
• Experience in core industry product R&D or hands-on experience with the latest technologies is preferred.

Skills

Diffusion models

Autoregressive generation

PyTorch

Distributed training

Video generation

Video VAE

Tokenizers

First-author papers

Research publications

End-to-end projects

Industry R&D experience

Education

PhD candidate in AI-related fields

Tools

PyTorch

Job description

Lightspeed Tech Center at Lightspeed Studios is pursuing advanced research to design and iterate on next-generation video generation foundations. The role focuses on long-context attention, memory mechanisms, tokenizers, and scaling laws for multi-resolution video. You will lead experiments, define data strategies, and publish results as part of a cutting-edge R&D team developing PUBG Mobile and other top games.