AI Audio Codec Algorithm and Standardization Engineer

Team Introduction Welcome to Video Arch Intelligent Immersive Audio Team! We are dedicated to pushing the boundaries of immersive audio technology and standardization. In addition to supporting TikTok requirements including short video, live-streaming, content creation tools and also VR/AR experiences, we also stay up-to-date with the latest research in the industry and participate in audio Standards Developing Organizations(SDO) such as MPEG, 3GPP, and IETF, etc. As part of our commitment to innovation, we proactively conduct R&D using Machine Learning and NN models(especially generative models) for immersive audio technology. If you're looking to work with a team that values creativity, innovation, and collaboration, we'd love to hear from you. Please join us to reshape the audio world together.

Responsibilities

• Develop a high compression rate full-band AI audio codec algorithm system based on generative frameworks. Research and apply model architectures such as VQ-VAE, GAN, and Diffusion to audio feature representations and high-quality AI audio codec systems. - Follow and research the next-generation audio codec system for machines. Build underlying technologies for machine-oriented intelligent audio representation and interaction. - Participate in the development of domestic and foreign audio standards and supporting systems, including domestic UWA, AVS standard organizations, and international 3GPP SA4, MPEG-IWG6, IETF, MPAI, etc.