I'm a software engineer at UKG, about a year in. I work on the layer underneath our AI features. That means tracing, so an on-call engineer can follow one request across a lot of services instead of guessing which one broke. It also means Go pipelines that move that data around Google Cloud, and an internal server that lets teams across the company plug their own tools into UKG's AI assistant.

I'm also building Gateway. You design a system on a canvas, five AI agents review it while you draw and point out the weak spots, and the finished design turns into a real deployment. It's live at gatewayinfra.ai with users outside the team. It's a company I'm building, and it has taught me more than anything else I've worked on.

Before UKG I worked closer to the hardware. My senior capstone was firmware and audio processing for a small recording device, and before that I built an SMS app so people without internet could reach an LLM by text message. I spent a stretch on deep learning too, mostly rebuilding published models to understand how they worked.

The problems I like are the ones where machine learning, infrastructure, and real users meet.