Next-Gen Video AI Research Intern

Tencent International Service Pte. Ltd.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Lightspeed Studios is seeking a PhD-level AI researcher to advance video generation technologies and large-scale foundation models. You will work on diffusion-based and autoregressive systems, with a focus on multi-resolution video and tokenization strategies.

Responsibilities include designing scalable architectures, leading pre-training efforts, and publishing findings. Collaboration across engine, QA, AI, and next-gen game teams is expected.

Qualifications

• PhD in AI-related fields with first-author publications in top-tier venues.
• Strong practical experience implementing diffusion and autoregressive video generation models.
• Proficiency in PyTorch and large-scale distributed training.

Responsibilities

• Design and iterate on next-generation video generation foundation architectures.
• Explore core technologies for long video generation and multi-frame-rate processing.
• Research high-compression-ratio video tokenizers and unified modeling approaches.
• Lead video pre-training at large token scales and define data mixtures.
• Define scaling laws and scientific paths to improve model capabilities.
• Publish papers and drive technical roadmap decisions based on experiments.

Skills

Diffusion models

Video generation

PyTorch

Distributed training

Research publications

Education

PhD in AI

Tools

PyTorch

Job description

Lightspeed Studios is seeking a PhD-level AI researcher to advance video generation technologies and large-scale foundation models. You will work on diffusion-based and autoregressive systems, with a focus on multi-resolution video and tokenization strategies.

Responsibilities include designing scalable architectures, leading pre-training efforts, and publishing findings. Collaboration across engine, QA, AI, and next-gen game teams is expected.