About this role
Design and iterate on next-generation video generation foundation architectures, focusing on long video generation and high-compression tokenizers. Lead large-scale pre-training, define scaling laws, and publish academic research on state-of-the-art video models.
Requires a Ph.D. in AI-related fields with a strong publication record and 3+ years of research experience in Video VAE/Tokenizers. Must be proficient in PyTorch and have experience training large-scale image or video generation models from scratch.
What they're looking for
Required
- •Ph.D. in AI-related fields with strong publication record
- •+ years of research experience in Video VAE/Tokenizers
- •Proficient in PyTorch
- •Experience training large-scale image or video generation models from scratch
Frequently asked questions
What does a Video Generation Foundation Model Researcher at LIGHTSPEED STUDIOS do?
Design and iterate on next-generation video generation foundation architectures, focusing on long video generation and high-compression tokenizers. Lead large-scale pre-training, define scaling laws, and publish academic research on state-of-the-art video models. Requires a Ph.D. in AI-related field…
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, Tokenizers.
How much does a Video Generation Foundation Model Researcher at LIGHTSPEED STUDIOS 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 LIGHTSPEED STUDIOS's careers page. ApplyLah can tailor your résumé and cover letter to this exact role in seconds first.