Machine learning · Computer vision · LLM systems
Applied scientist turned technical co-founder. Most recently built a real-time voice agent and live video classroom; before that, computer vision models that run on amazon.com.
PhD from the University of Washington, then IBM Research, five years at Amazon, and since 2025 co-founder and CTO of FluenTea, where I designed and built the product, from the voice agent to the Android app.
FluenTea is a video classroom with an AI speaking coach, ChaCha, for language schools. Every class and practice call is transcribed, and from the transcripts the teacher learns how long each student spoke, and each student and teacher gets feedback. I built the coach, the video classroom and the continuous feedback loops that improve the product from user behavior. In the first university pilot, most students kept practicing with her for longer than their teachers had required. I helped manage a team of six part-time advisors, from language teachers to UX and product designers.
Language schools run live classes in it and the AI coach runs practice calls between classes. I designed and built the engineering infrastructure, frontend, video platform and AI coach as the technical co-founder.
Technical lead on three computer vision projects that went to production on amazon.com and Alexa, including a text-VQA model that filled in sizes for more than ten million products. Amazon global Door Desk award.
Led GTE, a table extraction system (WACV 2021), built the TableLab labeling tool around it, and organized a SemEval 2021 shared task. My PhD work on decoding behavior from brain recordings and video was an oral at AAAI 2018.
I love brains and computers, basically any cognitive system. I was born in Nanjing, grew up in Canada, and have lived in Berlin since 2021, where I am slowly learning German. I like living inside other cultures, and role-playing and strategy games (Dragon Age and XCOM most of all).