About this role
Design and iterate on next-generation video generation foundation architectures and explore core technologies for long video generation. Lead large-scale video pre-training, define scaling paths, and publish academic papers on state-of-the-art research.
Requires a Ph.D. in AI-related fields with a strong publication record at top-tier conferences. Candidates must have 3+ years of research experience in Video VAE/Tokenizers and proficiency in PyTorch and large-scale distributed training.
What they're looking for
Diffusion ModelsAutoregressive GenerationPyTorchDistributed TrainingVideo VAEVideo TokenizersLong-context AttentionKV Cache Compression
Frequently asked questions
What does a Video Generation Foundation Model Researcher at Tencent do?
Design and iterate on next-generation video generation foundation architectures and explore core technologies for long video generation. Lead large-scale video pre-training, define scaling paths, and publish academic papers on state-of-the-art research. Requires a Ph.D. in AI-related fields with a s…
What skills does this Video Generation Foundation Model Researcher role need?
Key skills for this role include Diffusion Models, Autoregressive Generation, PyTorch, Distributed Training, Video VAE, Video Tokenizers.
How much does a Video Generation Foundation Model Researcher at Tencent pay?
The employer did not list a salary for this role. Most similar Singapore roles publish their band on the job page.
Is this Video Generation Foundation Model Researcher role remote, hybrid, or on-site?
This role is on-site, based in Singapore.
How do I apply for this Video Generation Foundation Model Researcher role?
You can apply directly on Tencent's careers page. ApplyLah can tailor your résumé and cover letter to this exact role in seconds first.