Summary
Xiaoqin Feng is an AI engineering specialist with nine years of experience turning research into production-grade multimodal systems, currently advancing context-aware home intelligence at Wyze and researching LLM agents at USC. She has built and scaled LLM-based agent frameworks with tool calling, multi-agent orchestration, safety guardrails, and runtime monitoring, and launched high-fidelity speech-LLM models achieving real-time factors and MOS scores suitable for production. Her expertise spans end-to-end speech-centric pipelines (ASR, TTS, voice cloning, style transfer), large-scale multimodal data engineering handling millions of daily requests and millions of hours of audio, and reliable distributed services with 99%+ uptime. Comfortable bridging academia and industry, she mentors interns and translates prototypes into robust services that drive revenue, while her GitHub ethos—Keep Patience And Passion—reflects a measured, research-informed approach to engineering.
9 years of coding experience
5 years of employment as a software developer
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at University of Southern California
Master of Science - MS, Computer Software Engineering, Master of Science - MS, Computer Software Engineering at Beijing University of Technology