Tencent Youtu Lab Research Intern - Multimodal Large Language Models (2026 Project UP)

Tencent Youtu Lab is recruiting a Research Intern for the 2026 Project UP initiative to work on Multimodal Large Language Models (MLLMs). The role focuses on R&D combining image, text, audio, and video modalities, aiming to bridge theoretical advances with real-world industry applications. The intern will collaborate with senior researchers to pursue multimodal pre-training, long-video interaction, and visual reasoning research and contribute to publications or open-source outputs.