Real work, written up the same way each time: what I built, what broke, and what I learned.
Built
A platform that crawls any public website, converts its content into structured data, audits it for AI search visibility, and recommends fixes. I built the universal scraping layer, the core AI modules and the backend that scores and tracks content in real time.
Built
A centralized AI search engine using Retrieval-Augmented Generation, shipped in 2024. It keeps products in sync from four backend systems, serves three frontends through one search API, handles complex product catalogs with many variations in size, model, memory and storage, and solved the client's main search problem.
Built
I led the development of a distributed scraping system that cut end-to-end processing time from 4.5 hours to under an hour, about 75%, and lowered infrastructure cost by about 40%.
Built
A search workflow you can talk to. I integrated a voice API, converted speech to text, and passed the transcribed query into a retrieval-augmented pipeline that returns relevant results from indexed knowledge sources.
Built
PostGIS-backed proximity search: finding all matching records within a set distance of a position, for location-aware application features.