AI Engineering

I build AI systems you can measure.

Portrait of Victor Mendez

I’m Victor Mendez. After almost a decade in oil and gas and 5+ years in BI and data across fintech, healthcare and agritech, I now work on retrieval-augmented generation, conversational assistants and predictive models, backing every decision with specs, tests and reproducible metrics.

Projects

5 projects

  1. Economicon, a FinOps assistant

    A multi-tenant assistant that ingests Azure costs and answers natural-language questions using semantic retrieval scoped to each customer. My master’s thesis, built as a team.

    Platform · RAG · LLM

    2026

  2. Vicky, a voice assistant for a clinic

    Books medical appointments and answers patients’ questions out loud. Built on Dialogflow, a FastAPI webhook and Gemini over OCR-processed documents, and it doesn’t make things up when it doesn’t know.

    Voice · LLM · RAG · Vector search

    2026

  3. Aurum Market, semantic catalogue search

    A product discovery engine over 15,000 Spanish-language products, built on Qdrant and E5 embeddings. It searches by intent and catches duplicate listings, with no LLM at runtime.

    Vector search

    2026

  4. Tenerife travel assistant

    A chat over a PDF travel guide. It retrieves with ChromaDB, answers with GPT-4.1-mini and tool calling while citing its source, and ships as a Streamlit app built on a reusable Python package.

    LLM · RAG · Vector search

    2026

  5. Hotel cancellation prediction

    A cancellation classifier over 119,390 bookings, with a 15-algorithm benchmark, data leakage detection and an Optuna-tuned LightGBM that reaches F1 0.85 and ROC-AUC 0.96.

    Machine learning

    2026