Computer Vision Research Intern

Tencent

  • Singapore
  • Training
  • Full-time
  • 1 month ago
Responsibilities: Level Infinite is a global game publisher offering a comprehensive network of bespoke services for games, development teams and studios around the world. We are dedicated to delivering engaging and original gaming experiences to a worldwide audience, whenever and wherever they choose to play, while building a community that fosters inclusivity, connection, and accessibility. The brand also provides a wide range of services and resources to our network of developers and partner studios around the world to help them unlock the true potential of their games. Level Infinite is both publisher of breakout hit games like PUBG MOBILE and Goddess of Victory: NIKKE, and a collaborative partner in games such as Fatshark’s Warhammer 40,002: Darktide, Dune: Awakening from Funcom, Nightingale from Inflexion Studios and many more. To learn more about Level Infinite, visit levelinfinite.com, and follow on Twitter, Facebook, Instagram and YouTube. Job Responsibilities 1.Responsible for researching and developing advanced algorithms and technologies for multimodal understanding, image and video generation, and 3D visual understanding; 2.Design and optimize algorithm models for advertising business scenarios, improve the accuracy and efficiency of algorithms; 3.Responsible for conducting research on cutting-edge large-scale model technology and AIGC technology, exploring the possibility of application in business scenarios; 4.Work closely with team members to complete the development, testing, and deployment of projects.Requirements: Job Requirements 1.Major in image processing/computer vision/machine learning/artificial intelligence or related fields, with a master's degree or above; 2.Proficient in the fundamental knowledge of computer vision, machine learning, and deep learning algorithms; 3.Proficient in image or video generation-related algorithms, familiar with common generative models, such as GAN, Stable Diffusion, ControlNet, LoRA, etc.; 4.Proficient in 3D visual algorithms, such as monocular motion capture, character lip generation, and 3D scene understanding; 5.Good programming skills, familiar with data structure and algorithms; 6.Good analyzing and modeling, problem discovery and solving abilities, good business understanding ability and teamwork and communication skills, and excellent self-motivation; 7.Having published top conference/journal papers or participated in relevant competitions and achieved good results is priority.

Tencent