Research Scientist - Speech & Audio Understanding (Speech Generation)

Tencent • Bellevue, WA

8d

About The Position

Business Unit What the Role Entails Job Responsibilities: 1. Track the latest research in speech generation algorithms, explore next-generation paradigms for speech/audio generation, and push the boundaries of speech generation capabilities. 2. Investigate cutting-edge multimodal voice foundation model technologies to enhance voice interaction experiences by integrating text, speech, and vision. 3. Lead the technical R&D of voice foundation models, driving model performance improvements and innovative applications. Who We Look For Job Requirements: 1. Master’s or Ph.D. in Computer Science, Artificial Intelligence, Electronic Engineering, Signal Processing, or related fields. 2. Research or development experience in one or more areas: voice foundation models, speech synthesis, speech recognition, audio generation, voice conversion, or speech codec. 3. Familiarity with mainstream voice-enabled large models (e.g., GPT4o, GLM-4-Voice, Qwen2.5-Omni, Voila). Prior project experience is preferred. 4. Proficient in deep learning frameworks (e.g., PyTorch). Experience with large-scale model training frameworks (Megatron/Deepspeed) is a plus. 5. Solid understanding of large model architectures and principles. Experience in large-scale pretraining or post-training is preferred.

Requirements

• Master’s or Ph.D. in Computer Science, Artificial Intelligence, Electronic Engineering, Signal Processing, or related fields.
• Research or development experience in one or more areas: voice foundation models, speech synthesis, speech recognition, audio generation, voice conversion, or speech codec.
• Familiarity with mainstream voice-enabled large models (e.g., GPT4o, GLM-4-Voice, Qwen2.5-Omni, Voila). Prior project experience is preferred.
• Proficient in deep learning frameworks (e.g., PyTorch). Experience with large-scale model training frameworks (Megatron/Deepspeed) is a plus.
• Solid understanding of large model architectures and principles. Experience in large-scale pretraining or post-training is preferred.

Responsibilities

• Track the latest research in speech generation algorithms, explore next-generation paradigms for speech/audio generation, and push the boundaries of speech generation capabilities.
• Investigate cutting-edge multimodal voice foundation model technologies to enhance voice interaction experiences by integrating text, speech, and vision.
• Lead the technical R&D of voice foundation models, driving model performance improvements and innovative applications.

Benefits

• Employees hired for this position may be eligible for a sign on payment, relocation package, and restricted stock units, which will be evaluated on a case-by-case basis.
• Subject to the terms and conditions of the plans in effect, hired applicants are also eligible for medical, dental, vision, life and disability benefits, and participation in the Company’s 401(k) plan.
• The Employee is also eligible for up to 15 to 25 days of vacation per year (depending on the employee’s tenure), up to 13 days of holidays throughout the calendar year, and up to 10 days of paid sick leave per year.
• Your benefits may be adjusted to reflect your location, employment status, duration of employment with the company, and position level.
• Benefits may also be pro-rated for those who start working during the calendar year.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Number of Employees: 5,001-10,000 employees