Senior Video Generation Research Scientist

LightSpeed Studios; Singapore; On-site; SGD 180,000 - 250,000; Full time

Job summary

Lightspeed Studios is seeking a PhD-level researcher to design next-generation video generation foundations. You will explore diffusion-models and autoregressive approaches, lead large-scale pre-training, and publish findings while guiding technical roadmaps.

We value first-author AI publications and experience with video/image generation models, distributed training, and PyTorch. Join our multi-genre, cross-device game research effort in Singapore.

Qualifications

• PhD in AI-related fields with first-author papers.
• Proficient in diffusion models and autoregressive generation.
• Experience training video/image generation models from scratch.
• Strong PyTorch skills and large-scale distributed training.
• Publications in video generation or diffusion models.
• Experience leading end-to-end video foundation model projects preferred.

Responsibilities

• Design and iterate on the next-generation video generation foundation architecture.
• Explore core technologies for long video generation, including long-context attention and memory mechanisms.
• Lead video pre-training at large token scale and define data mixture strategies.
• Track state-of-the-art, run comparative experiments, publish papers, and set the technical roadmap.

Skills

PyTorch

Distributed training

Diffusion models

Video generation

Autoregressive models

Education

PhD in AI/ML

Tools

Python

GPU compute

Job description

Lightspeed Studios is seeking a PhD-level researcher to design next-generation video generation foundations. You will explore diffusion-models and autoregressive approaches, lead large-scale pre-training, and publish findings while guiding technical roadmaps.

We value first-author AI publications and experience with video/image generation models, distributed training, and PyTorch. Join our multi-genre, cross-device game research effort in Singapore.