Multimodal Speech AI Scientist

Lightspeed Studios; Bellevue (WA); On-site; USD 123,000 - 230,000; Full time

Benefits offered by this job

Sign-on bonus

Relocation package

RSUs

Job summary

Tencent in Bellevue, WA is seeking researchers to develop large-scale, native multimodal model systems that jointly support vision, audio, and text for comprehensive perception and understanding of the physical world.

The role focuses on end‑to‑end speech models, representation learning, and cross‑modal alignment with potential collaboration across image and text modalities. Requires advanced degrees and strong background in speech processing.

Qualifications

• Ph.D. in Computer Science, Electrical Engineering, Artificial Intelligence, Linguistics, or a related field; or Master’s degree with several years of relevant experience.
• Solid understanding of speech and audio signal processing, acoustic modeling, language modeling, and large model architectures.
• Proficient in core speech system pipelines such as ASR, TTS, or speech translation; multilingual/multitask/end-to-end experience is a plus.

Responsibilities

• Develop general‑purpose, end‑to‑end large speech models across multilingual ASR, translation, synthesis, and understanding.
• Advance research on speech representation learning and encoder/decoder architectures for unified acoustic representations.
• Explore alignment and fusion between audio/speech and other modalities for multimodal training/inference.
• Build and maintain high‑quality multimodal speech datasets with annotation and data synthesis.

Skills

Speech processing

Acoustic modeling

Language modeling

Transformer architectures

Multimodal training

Distributed systems

PyTorch

TensorFlow

Education

Ph.D. or Master’s degree in CS/EE/AI/Linguistics

Relevant experience after degree

Tools

PyTorch

TensorFlow

Job description

Tencent in Bellevue, WA is seeking researchers to develop large-scale, native multimodal model systems that jointly support vision, audio, and text for comprehensive perception and understanding of the physical world.

The role focuses on end‑to‑end speech models, representation learning, and cross‑modal alignment with potential collaboration across image and text modalities. Requires advanced degrees and strong background in speech processing.