📋 Job Overview

We are building a large-scale multimodal model system natively supporting vision, audio, and text to enable comprehensive perception and understanding of the physical world by AI systems. You will join the core research team in the speech and audio direction, focusing on key research tasks such as developing end-to-end speech large models with universal capabilities. This includes advancing speech representation learning, exploring alignment and fusion mechanisms in multimodal models, and building high-quality datasets.