Yuelin Ou

I’m a data and AI engineer based in Los Angeles. I grew up in Yunnan, in southwest China, and studied mathematics at the University of Rochester.

My current work splits between two places. By day, I build and operate production data integration pipelines at INTO University Partnerships — the kind of work where what matters most is what doesn’t happen: a record that doesn’t get duplicated, a write that doesn’t silently drop, a downstream system that doesn’t lose state when an upstream service hiccups. Outside of that, I build AI-native tools — an offline AI math classroom for low-resource environments, an entitlement screener for residential real estate — where the same instinct shows up in a different form: making sure the system actually does what it claims to do.

What I’m drawn to, across both, is the work of closing the gap between what software claims to do and what it actually does. Audit trails over reassuring dashboards. Systems that can prove their own consistency over systems that look right at a glance. Tools that fail loudly and locally over tools that fail quietly and at scale.