Video Foundation Models Research Intern

Tencent

Singapore

On-site

SGD 120,000 - 180,000

Full time

6 days ago

Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Lightspeed Tech Center, a Tencent R&D unit, seeks a PhD candidate focusing on video generation foundation models. You will design and iterate architectures, explore long video generation tech, and lead pre-training at scale using PyTorch and distributed training.

Applicants should have first-author papers in AI, experience with diffusion models, and publications in video generation. Collaboration across engineering and research to advance game-related video tech is expected.

Qualifications

Currently pursuing Ph.D. with first-author papers at top-tier conferences.
Proficient in 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 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.

Responsibilities

Design and iterate on next-generation video generation foundation architecture.
Explore core technologies for long video generation (long-context attention, KV Cache compression, memory mechanisms).
Lead video pre-training at large token scale, define data mixture and curriculum learning strategies.
Publish academic papers; drive technical roadmap decisions; track industry state-of-the-art.