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

Business Unit

Cloud & Smart Industries Group (CSIG) is responsible for promoting the company's cloud and industry Internet strategy. CSIG explores the interactions between users and industries to create innovative solutions for smart industries via technological advancements such as cloud, AI, and network security. While driving the digitalization of retail, medical, education, transportation and other industries, CSIG helps companies serve users in smarter ways, building a new ecosystem of intelligent industries that connect users and businesses.

What the Role Entails

Tencent Youtu Lab is seeking a highly motivated Research Intern to join our 2026 Project UP initiative, focusing on Multimodal Large Language Models (MLLMs). This role is ideal for postgraduate students passionate about AI research and looking to contribute to the next generation of intelligent systems. The intern will engage in cutting-edge R&D involving the integration and understanding of diverse data types such as image, text, audio, and video. You will work alongside top researchers to explore advanced techniques like multimodal pre-training, long-video interaction, and visual reasoning, bridging theoretical innovation with real-world applications. This is a unique opportunity to develop impactful solutions, contribute to open-source or academic outputs, and push the frontier of AI at Tencent Cloud.

Responsibilities

• Core Research & Development: Conduct advanced research on technical solutions for Multimodal Large Models (MLLMs), focusing on the perception, understanding, and interaction of mixed modalities including image, text, audio, and video. Explore cutting-edge topics such as native multimodal pre-training schemes, long-video interactive understanding, visual reasoning, and multimodal agents.
• Innovation & Breakthroughs: Keep pace with state-of-the-art (SOTA) trends in the multimodal large model field. Combine theoretical research with actual business scenarios to explore innovative solutions, achieve technical breakthroughs, and build industry-leading multimodal large language models.
• Industry Impact: Produce influential research outcomes and contribute to the advancement of multimodal large model technologies within the industry through high-quality papers or open-source projects.

Who We Look For

• Currently pursuing a postgraduate degree (Master’s or PhD) in Computer Science, Artificial Intelligence, Machine Learning, or related fields, familiar with key research achievements and mainstream open-source projects in the field of multimodal large language models. Demonstrated strong academic research capabilities with a track record of results, and practical experience in solving concrete algorithmic problems.
• Strong algorithm implementation skills with proficiency in Python. Demonstrate extensive knowledge of mainstream deep learning platforms and algorithmic frameworks applied in Multimodal Large Models (MLLMs) and foundation models.
• Excellent analytical and problem-solving skills. Passionate about tackling challenging technical problems and possesses a strong spirit of teamwork and collaboration.
• Excellent proficiency in both English and Chinese Mandarin, written and spoken, to effectively collaborate with global research and engineering teams.

#LI-JY1

Equal Employment Opportunity at Tencent

As an equal opportunity employer, we firmly believe that diverse voices fuel our innovation and allow us to better serve our users and the community. We foster an environment where every employee of Tencent feels supported and inspired to achieve individual and common goals.