Senior Researcher, Speech Synthesis & Multimodal LLMs

L&Q OASIS PTE. LTD.; Singapore; Hybrid; SGD 120,000 - 180,000; Full time

Job summary

Tencent's Lightspeed Tech Center is seeking a PhD-level researcher to advance speech synthesis and multimodal LLMs for real-time spoken interaction. You will prototype and productionize TTS, voice conversion, and audio generation within online applications, collaborating with cross-functional teams to scale experiments to deployment.

Strong background in speech processing, diffusion/autoregressive models, and Python-based DL frameworks is essential; publications at top venues are a plus.

Qualifications

• Ph.D. in Computer Science, Electrical Engineering, Signal Processing, or closely related field.
• Strong foundation in speech/audio processing and modern generative models.
• Hands-on experience extending LLMs to speech/audio modalities.
• Experience with real-time interaction modeling is a plus.

Responsibilities

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

Skills

Python

Deep Learning

Speech Processing

TTS

Multimodal LLM

Education

Ph.D. in CS/EE/Signal Processing

Tools

PyTorch

TensorFlow

Job description

Tencent's Lightspeed Tech Center is seeking a PhD-level researcher to advance speech synthesis and multimodal LLMs for real-time spoken interaction. You will prototype and productionize TTS, voice conversion, and audio generation within online applications, collaborating with cross-functional teams to scale experiments to deployment.

Strong background in speech processing, diffusion/autoregressive models, and Python-based DL frameworks is essential; publications at top venues are a plus.