Immersive Audio AI Research Scientist

TikTok; Sydney; On-site; AUD 120,000 - 190,000; Full time

Job summary

TikTok's Multimedia Lab Audio Innovation team in Sydney is seeking researchers to push immersive audio technology through ML models, codec optimization, and participation in international audio standards.

You will prototype self-developed algorithms for immersive audio understanding, work on short video, live streaming, VR/AR contexts, and collaborate with cross-functional teams shaping future audio experiences.

Qualifications

• Master's degree or above in electronic information, computer, multimedia, Machine Learning, AI.
• PhD degree majors in related fields preferred.
• Experience with 3D Spatial Audio rendering, GAN/Diffusion audio processing, voiceprint/wake-up, sound event detection, automatic speech recognition, NLP.

Responsibilities

• Research and implement the department's self-developed next-generation immersive intelligent audio understanding and processing algorithm system.
• Implement and optimize immersive intelligent audio codec and processing system for short Video On Demand, LIVE, VR/MR and other scenarios.
• Follow up and participate in domestic and international audio standards, write high-quality technical proposals, and promote standard work.

Skills

3D Spatial Audio

GAN/Diffusion audio

Voiceprint wake-up

Sound event detection

Automatic Speech Recognition

Natural Language Processing

Python

C++

TensorFlow

PyTorch

Kaldi

English communication

Education

Master's degree or above in electronic information / computer / multimedia / ML / AI

PhD preferred

Tools

Kaldi

TensorFlow

PyTorch

Job description

TikTok's Multimedia Lab Audio Innovation team in Sydney is seeking researchers to push immersive audio technology through ML models, codec optimization, and participation in international audio standards.

You will prototype self-developed algorithms for immersive audio understanding, work on short video, live streaming, VR/AR contexts, and collaborate with cross-functional teams shaping future audio experiences.