Software Engineer.

Growing up in Tanzania, I saw how unreliable internet and paper-based administration can slow down everyday school operations. I wanted the core records workflow to remain useful without a network connection.

I built a Java and Python system backed by SQLite, using object-oriented design, automated CRUD workflows, and a normalized relational schema to manage student and administrative records locally.

Useful student information is scattered across documents, while general chatbots can answer confidently without evidence. I wanted a narrow assistant whose answers could be traced back to known sources.

I built a Python RAG pipeline over a 10-document knowledge base, producing 47 embedded segments in ChromaDB and retrieving the top four sources for Groq's Llama 3.3 model. The system includes source attribution and strict refusal behavior.

Students managing tight budgets should not need a complicated spreadsheet or an oversized finance app to understand where their money is going.

I built a Flask backend and JavaScript frontend with Google OAuth, session-based authentication, budget tracking, email notifications, CSV export, and a normalized SQLite schema.