Skip to content
View mttpzz's full-sized avatar
1 follower · 2 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report mttpzz

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
mttpzz/README.md

Hi, I'm Matteo 👋

I am an AI Developer specializing in LLM-based solutions, Generative AI frameworks, and business process automation. With a background in Computer Engineering from Politecnico di Milano and 7+ years of experience in IT systems development and management, I bridge the gap between cutting-edge AI innovations and production-ready enterprise tools.

🔭 What I'm Currently Working On

  • LLM Solutions & GenAI Frameworks: Researching and implementing Python-based AI architectures using Cheshire Cat and Open WebUI.
  • LLMOps & Observability: Routing model traffic through a LiteLLM gateway for unified multi-provider access, and instrumenting it with Langfuse for tracing, cost tracking, and output-quality evaluation.
  • Document Intelligence & Prototyping: Developing custom AI tools to streamline enterprise document management and internal processes.
  • AI Innovation & Strategy: Experimenting with emerging AI technologies to evaluate their integration and strategic value within business contexts.

🛠️ Tech Stack & Tools

  • Programming Languages: Python | SQL | R
  • AI & Data Frameworks: TensorFlow | PyTorch | Scikit-Learn | Pandas
  • GenAI, Agents & Automation: LangChain | Cheshire Cat | Open WebUI | AnythingLLM | Goose | n8n
  • LLMOps & DevOps: LiteLLM | Langfuse | Docker | Git
  • Enterprise Systems: Magento | PIM

🎓 Education & Background

  • M.Sc. in Computer Science & Engineering – Politecnico di Milano (2015 - 2017)
  • B.Sc. in Computer Engineering – Politecnico di Milano (2011 - 2014)

🔬 Projects

  • pdf2qa: Python tool that automatically generates question-answer datasets from PDFs.
  • met-me: LLM-powered Telegram bot with RAG and emotion detection.
  • nba-weekres-bot: Weekly NBA recap bot on Telegram.

University projects (Politecnico di Milano)

  • PiCoNet: Built a neural network in Python & TensorFlow to compute the pitch of human voice signals (NLP).
  • Recommender System Challenge (Kaggle): Job recommendation algorithm based on user search history in Python.
  • Taxi Trajectory Prediction (ECML/PKDD): Destination prediction using data mining techniques in R.

📫 Connect with Me

Pinned Loading

  1. met-me met-me Public

    LLM-powered Telegram bot for emotional support with RAG, emotional state tracking, and GDPR compliance. Built with Claude, LlamaIndex, Chroma and SQLite.

    Python

  2. nba-weekres-bot nba-weekres-bot Public

    Weekly NBA recap on Telegram: results, top performances (Hollinger Game Score) and standings, free via GitHub Actions + ESPN's public APIs

    Python

  3. pdf2qa pdf2qa Public

    Python tool to automatically generate question-answer datasets from PDF documents using Claude API. Supports multi-page extraction, balanced Q&A distribution, and CSV export.

    Python

  4. repomind repomind Public

    Multi-Agent RAG assistant for codebase ingestion and QA. Features LlamaIndex, CrewAI agents, ChromaDB vector search, BGE Cross-Encoder reranking, and native Langfuse MLOps tracing.

    Python