Generative AI Research Intern - Multimodal & 3D

Tencent; Greater London; On-site; GBP 70,000 - 120,000; Full time

Job summary

Level Infinite in London is seeking a researcher to develop multimodal understanding, image and video generation, and 3D generation technologies for games. You will research large models and Generative AI and collaborate with the team on development, testing and deployment.

Ideal candidates hold a Master’s in a relevant field, with strengths in computer vision, ML, DL, and generative models, plus strong programming and teamwork capabilities. London-based role with on-site work assumed.

Qualifications

• Master's degree or above in Image Processing/Computer Vision/Machine Learning/Artificial Intelligence or related fields.
• Proficient in computer vision, machine learning, and deep learning algorithms.
• Proficient in image or video generation algorithms, familiar with generative models such as GAN, Stable Diffusion, ControlNet, LoRA, and DreamFusio.
• Proficient in 3D vision algorithms or 3D generation-related algorithms, such as monocular motion capture, lip sync generation, and 3D scene understanding and generation.
• Strong programming skills, familiar with data structures and algorithms.
• Strong analytical modeling, problem-solving abilities, good business understanding, teamwork, and communication skills, and excellent self-motivation.
• Preference will be given to candidates with relevant top conference/journal papers or those who have achieved good results in related competitions.

Responsibilities

• Responsible for researching and developing advanced algorithms and technologies related to multimodal understanding, image and video generation, and 3D generation.
• Research cutting-edge large model and Generative AI technologies, exploring their potential applications in game development scenarios.
• Collaborate closely with team members to complete project development, testing, and deployment.

Skills

Computer Vision

Machine Learning

Deep Learning

3D Vision

Programming

Education

Master's degree in AI/CS

Tools

GAN

Stable Diffusion

ControlNet

LoRA

DreamFusio

Job description

Level Infinite in London is seeking a researcher to develop multimodal understanding, image and video generation, and 3D generation technologies for games. You will research large models and Generative AI and collaborate with the team on development, testing and deployment.

Ideal candidates hold a Master’s in a relevant field, with strengths in computer vision, ML, DL, and generative models, plus strong programming and teamwork capabilities. London-based role with on-site work assumed.