Sobre esta vaga de Senior Researcher, Speech Synthesis and Multimodal LLM｜高级研究员 - 语音合成与多模态大模型 na Tencent
Business Unit
LIGHTSPEED STUDIOS is made up of passionate players who advance the art & science of game development through great stories, great gameplay, and advanced technology. We are focused on bringing next generation experiences to gamers who want to enjoy them anywhere, anytime, across multiple genres and devices.About the Hiring Team
Lightspeed Tech Center is a R&D department under Lightspeed Studios which develop PUBG Mobile and other high-quality games. Our Tech Center leads the research, exploration, and discovery of innovative technologies and provides technical services for all games during all phases of life cycle, including engine, audio, QA, AI, next generation game, technical cooperation, etc.What the Role Entails
Job Responsibilities
●Research and develop advanced speech synthesis and generation algorithms (e.g., TTS, voice conversion, sound/music generation) based on LLMs, multimodal/omnimodal LLMs.
●Develop and optimize speech and audio synthesis systems for online applications, improving effectiveness, efficiency, and scalability.
●Explore and advance full-duplex/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.
岗位职责
● 基于大语言模型（LLM）及多模态/全模态大模型，研究和开发前沿语音合成与生成算法（如 TTS、语音转换、声音/音乐生成等）。
● 开发和优化面向线上应用的语音及音频合成系统，提升效果、效率和可扩展性。
● 探索并推进全双工/流式多模态大模型在语音理解、语音生成及实时语音交互方面的能力。
● 与研究和工程团队跨职能协作，推动项目从原型验证到生产落地。
Who We Look For
Requirements
●Ph.D. in Computer Science, Electrical Engineering, Signal Processing, or a closely related field.
●Strong foundation in speech/audio processing and modern generative models (e.g., diffusion, flow matching, autoregressive, codec-based approaches).
●Hands-on experience extending LLMs to speech/audio modalities (e.g., 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.
●Proficient in Python and deep learning frameworks (e.g., PyTorch); experience with distributed training is a plus.
●Track record of publications at top-tier venues (e.g., ICML, NeurIPS, ICLR, ACL, ICASSP, Interspeech).
●Mandarin Chinese / Business-level Japanese or English
任职要求
● 计算机科学、电子工程、信号处理或相关领域博士学位。
● 具备扎实的语音/音频处理基础，熟悉现代生成模型（如扩散模型、流匹配、自回归模型、基于编解码器的方法等）。
● 具有将大语言模型扩展至语音/音频模态的实际经验（如语音分词器、多模态适配器、语音-文本联合训练等）；有全双工或流式语音对话系统及实时交互建模经验者优先。
● 熟练使用 Python 及深度学习框架（如 PyTorch）；有分布式训练经验者优先。
● 在顶级学术会议发表过论文（如 ICML、NeurIPS、ICLR、ACL、ICASSP、Interspeech 等）。
●中文/商务日语或英文
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.
