Senior Researcher, Speech Synthesis and Multimodal LLM

About the role

Tencent's Lightspeed Studios develops games such as PUBG Mobile, and its Lightspeed Tech Center is the R&D department responsible for research and technical services across engine, audio, QA, AI and next-generation game technologies. This Senior Researcher position focuses on speech synthesis and multimodal large language models.

Key responsibilities

• Research and develop advanced speech synthesis and generation algorithms (e.g., TTS, voice conversion, sound and music generation) based on LLMs and multimodal/omnimodal LLMs.
• Develop and optimize speech and audio synthesis systems for online applications, improving effectiveness, efficiency and scalability.
• Explore and advance full-duplex and streaming multimodal LLM capabilities in speech understanding, generation and real-time spoken interaction.
• Collaborate cross-functionally with research and engineering teams from prototyping to production.

Required profile

• Ph.D. in Computer Science, Electrical Engineering, Signal Processing or a closely related field.
• Strong foundation in speech/audio processing and modern generative models (diffusion, flow matching, autoregressive, codec-based approaches).
• Experience extending LLMs to speech/audio modalities (speech tokenizers, multimodal adapters, speech-text joint training).
• Experience with full-duplex or streaming spoken dialogue systems and real-time interaction modeling is a plus.
• Track record of publications at top-tier venues (ICML, NeurIPS, ICLR, ACL, ICASSP, Interspeech).

Required skills

• Proficiency in Python and deep learning frameworks such as PyTorch.
• Distributed training experience is a plus.