Projects

Internship search is high-volume and low-signal: hundreds of postings a day, few of them relevant. Internship Scout is my fix. I built it alone and keep adjusting it as I use it.

Each morning a GitHub Actions pipeline scrapes and dedupes postings from multiple sources, runs them through a deterministic eligibility rules engine, and ranks the survivors with LLM scoring that must cite verbatim text from the posting. Results land on a kanban board where I track every application to its outcome.

Pipeline runs are idempotent, and CI runs Vitest unit tests plus Playwright end-to-end tests.

An automation workflow connecting Google Calendar, Gmail, Telegram, Notion, and Google Sheets. It automated 12+ recurring scheduling and communication tasks and cut down on my manual scheduling errors. It was also the start of a habit I still keep: using AI tooling for personal productivity and for development.

Built as the capstone work of my Diploma in Artificial Intelligence at USMP (final grade 98%).