Hi This is
Tianshu Fu
AI-driven Engineer
AI-driven Engineer
Hi — I’m Tianshu (Tony) Fu, an AI-driven Data Engineer at Meta.
I design and deploy production-scale LLM tools, including:
Product Social Listening – a ChatGPT-style system that transforms millions of user comments into real-time product insights for Meta Quest and Ray-Ban.
[Blog]
LLM Taxonomy Assistant – automatically labels datasets and identifies coverage gaps, accelerating ML prompt experiments by weeks.
Previously, I was the founding engineer at Knowtex, where I built the first version of a RAG-powered voice AI platform that converts doctor-patient conversations into structured SOAP notes, helping reduce clinician burnout.
[App]
Master in statistics. Thing do taste on we manor.
Exchange in UC Berkeley, took three data science related courses
Bachelor in Computer Science
Lead engineer for two LLM-powered products: a real-time Product Social Listening platform and an LLM Taxonomy Assistant that together surface actionable insights for Reality Labs teams.
Built a RAG-powered voice-AI platform that translates doctor–patient conversations into personalized SOAP notes, cutting documentation time by 70 % and boosting note quality by 20 %.
Developed the seller-retention data pipeline and dashboard adopted by product managers to pinpoint churn drivers and steer growth strategy.
