Research Internship- Multimodal LLM (Speech/Music/Audio/Vision/Language)

Tencent

7d

About The Position

Business Unit Technology Engineering Group (TEG) is responsible for supporting the company and its business groups on technology and operational platforms, as well as the construction and operation of R&D management and data centers, TEG provides users with a full range of customer services. As the operator of the largest networking, devices, and data center in Asia,TEG also leads the Tencent Technology Committee in strengthening infrastructure R&D through internal and distributed open source collaboration, constructing new platforms and supporting business innovation. What the Role Entails About Tencent AI Lab at Seattle Area Tencent is a leading internet company in China. Tencent AI Lab at Seattle Area was established in May 2017. The lab strives to continuously improve AI's capability in perception, cognition, and creativity. Researchers there aim at solving challenging real-world problems with advanced technologies and publish extensively at top conferences and journals. Research Internship: Multimodal LLM (Speech/Music/Audio/Vision/Language) Tencent AI Lab is dedicated to advancing cutting-edge AI technologies, with a particular focus on innovative breakthroughs in large foundation models. The lab's long-term ambition is to drive the development of Artificial General Intelligence (AGI), and ultimately, Artificial Superintelligence (ASI). We are seeking research interns who are interested in developing novel speech/music/audio/vision/language processing techniques and large multimodal models for our Seattle area office located at Bellevue WA for the year 2026. Every research intern will work with researchers on a research project aimed at attacking one of the core problems by inventing cutting edge techniques. We encourage discussions and collaborations between researchers and interns. Interns are also encouraged to publish the results from the internship. Our projects span a wide range of areas, including developing more effective multimodal pretraining and post-training strategies for audio, speech, music, image, and video understanding and generation. We aim to enable fully duplex conversations, design more efficient large-model architectures, enhance multimodal memory and reasoning capabilities, and advance novel audio, speech, music, image, and video processing techniques—such as encoding, tokenization, and representation learning—with a focus on multimodal applications and end-to-end large models. Who We Look For

Requirements

• The ideal intern candidates are those who are Ph.D. students in computer science, electrical engineering, mathematics or a related field, are self-motivated and excited about developing novel techniques, have research experiences in natural language processing, speech, audio, and music processing, computer vision, dialog system, or machine learning, have good publication track records and history of creativity and intellectual flexibility, can program skillfully in Python and/or C++ and have experiences in using one of the leading deep learning toolkits.
• Intern duration: 3 months (with the possibility of extension).
• Can start any time in the year 2026.
• Location State(s) US-Washington-Bellevue

What This Job Offers

• Career Level: Intern
• Education Level: Ph.D. or professional degree
• Number of Employees: 5,001-10,000 employees