Presentation
Research Scientist-Video Understanding and Generation
SessionJob Postings
DescriptionWe are seeking a senior Research Scientist in video understanding and generation to lead next-generation research and development in intelligent media computing. With the rise of foundation models, video has become a critical modality for human–machine interaction, immersive content creation, and commercial applications such as smart advertising and large-screen experiences.
You will work on redefining how machines perceive, reason about, and generate video content—with a focus on delivering both technical breakthroughs and business impact.
Responsibilities:
1. Lead the architecture and development of core algorithms for video understanding, editing, and generation across key application scenarios.
2. Identify technical bottlenecks and opportunities for innovation in areas such as temporal representation, visual consistency, semantic editing, and content control.
3. Design and validate novel approaches for large-granularity video content generation, helping to establish new product experiences and differentiation.
4. Stay ahead of industry trends in video AI, foundation models, and generative technologies; define mid-to-long term strategies for competitive advantage.
You will work on redefining how machines perceive, reason about, and generate video content—with a focus on delivering both technical breakthroughs and business impact.
Responsibilities:
1. Lead the architecture and development of core algorithms for video understanding, editing, and generation across key application scenarios.
2. Identify technical bottlenecks and opportunities for innovation in areas such as temporal representation, visual consistency, semantic editing, and content control.
3. Design and validate novel approaches for large-granularity video content generation, helping to establish new product experiences and differentiation.
4. Stay ahead of industry trends in video AI, foundation models, and generative technologies; define mid-to-long term strategies for competitive advantage.
Location
Shanghai, Shenzhen, Hong Kong, Singapore, Canada, Beijing, Hangzhou, etc.
In-Person:
Onsite
Description of Position:
PhD; Full-Time
Other Skills or Experience:
1. Strong technical background in computer vision, deep learning, or related fields, with proven expertise in video analysis, generation, or editing.
2. Solid understanding of temporal modeling, scene understanding, video restoration, or generative techniques (e.g., GANs, transformers, diffusion models).
3. Familiarity with the application of large models (e.g., visual transformers, foundation models) to video data.
4. Experience bridging research and product, with a demonstrated ability to convert core technologies into commercial success.
5. PhD or equivalent experience in computer vision, machine learning, or video AI.
6. A strong record of publications, patents, or shipped products in video-related areas (e.g., CVPR, ICCV, SIGGRAPH, NeurIPS, etc.).
·
·
2025-08-01
Event Type
Job Posting
TimeSunday, 10 August 20258:00am - 9:00am PDT
LocationWest Building, Exhibit Hall C
Session TimeSunday, 10 August 20258:00am - 9:00am PDT
LocationWest Building, Exhibit Hall C
