I'm a Computer Science student at the University of Porto. I take web apps from database schema to deployed product with Next.js, FastAPI and PostgreSQL, and integrate AI through LLM APIs, RAG and embeddings where it solves a real problem.
Deployed apps, built end to end.
Swipe-based book recommendations. Readers swipe through books; a vector search over a shared book/reader space decides what comes next.
Next.js · TypeScript · Tailwind · FastAPI · PostgreSQL · pgvector
Invoice processing with a human in the loop. Invoices are extracted and validated automatically; the uncertain ones go to a review screen.
FastAPI · SQLAlchemy · PostgreSQL · Next.js · TypeScript · Docker · OpenAI API
An LLM-powered support backend that can act on orders safely: the model chooses the action, the code decides what's allowed.
Python · FastAPI · OpenAI API · RAG · ChromaDB · SQLite · Docker
Question answering over computer-vision papers with structure-aware chunking, hybrid retrieval and cited answers.
Python · FastAPI · Embeddings · ChromaDB
A spaced-repetition vocabulary trainer with typed recall in both directions, pronunciation playback and progress tracking.
JavaScript · Web Speech API · Local storage
I like owning the whole path of a feature: the schema and its migrations, the API, the interface people actually use, and the deployment, backups and auth around it.
When a product needs AI, I treat it as one more integration, not the whole product. The model extracts, retrieves or suggests; validation, permissions and business rules stay in code, and a person reviews whatever the system isn't sure about.
I'm available immediately, based in Porto, and happy to talk.
b0508181058@gmail.com