AIGC Algorithm Engineer: Diffusion & Multimodal

Shopee; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Shopee in Singapore is seeking an ML Researcher to design training pipelines for large-scale AIGC models, focusing on diffusion-based multimodal generation across image and video. You will contribute to architecture and system design, improving performance and quality in production settings.

Responsibilities include pioneering post-training methods, exploring new multi-modal capabilities, and publishing findings at top venues while delivering robust, production-grade implementations.

Qualifications

• Master's degree or above in Computer Science or related fields.
• First-author publication(s) at top-tier venues on diffusion-based multimodal generation.
• Experience in multimodal large models across image and video generation.
• Proficient in PyTorch.

Responsibilities

• Design training pipelines for large-scale AIGC models, including data curation and training stability.
• Architect and optimize diffusion-based multimodal models spanning image and video domains.
• Advance post-training methods to improve output quality.
• Prototype capabilities in multi-modal understanding and visual content generation.
• Track frontier research and contribute to production-grade implementations and publications.

Skills

Multimodal generation

Python

C++

CUDA

Team collaboration

Communication

Education

Master's degree in Computer Science or related fields

Tools

PyTorch

Job description

Shopee in Singapore is seeking an ML Researcher to design training pipelines for large-scale AIGC models, focusing on diffusion-based multimodal generation across image and video. You will contribute to architecture and system design, improving performance and quality in production settings.

Responsibilities include pioneering post-training methods, exploring new multi-modal capabilities, and publishing findings at top venues while delivering robust, production-grade implementations.