AI Engineer

Building intelligent systems from research to production.

Designing and building end-to-end AI solutions including Agentic RAG systems, multimodal document understanding, computer vision models, and data-driven IoT analytics. Ph.D. in Computer Science with a strong engineering foundation.

Generative AI & RAG
Multimodal AI & NLP
Computer Vision & Object Detection
ML Engineering & Data
Agentic AI & LLM Systems
Giovanni Pasqualino - AI Engineer

Professional Experience

Sep 2025 — Present

AI Engineer

BV TECH

Designing and implementing end-to-end RAG systems and production AI solutions. Working with LLMs, OCR, NER, multimodal models, and vector databases. Building scalable FastAPI services and resilient data extraction pipelines for production deployment.

Python FastAPI LLMs RAG OCR Vector DB Docker
Mar 2021 — Aug 2025

Software Engineer

Gest IoT

Developing architectures for managing, decoding, and translating data from WMBus, NB-IoT, and MQTT protocols, embedding AI modules for anomaly detection and predictive analytics on time-series. Designing and developing Android applications for WMBus data collection and workforce management, integrating AI modules for image analysis and OCR-based text recognition.

Android PostgreSQL MongoDB IoT Time Series
Sep 2019 — Sep 2020

Research Fellow

IPLAB · University of Catania

Designing and developing unsupervised domain adaptation algorithms for object detection and deep learning algorithms for processing egocentric data captured through Mixed Reality devices.

PyTorch Domain Adaptation Object Detection Mixed Reality
Mar 2019 — Jul 2019

Machine Learning Intern

STMicroelectronics

Designing and developing an anomaly detection system integrating forecasting and anomaly detection models through a voting-based decision mechanism on semiconductor manufacturing time-series.

Python Anomaly Detection Time Series Ensemble Models

Research & Publications

MITS-GAN: Safeguarding Medical Imaging from Tampering with Generative Adversarial Networks

Computers in Biology and Medicine (CBM), 2024

A Multi Camera Unsupervised Domain Adaptation Pipeline for Object Detection in Cultural Sites

Computer Vision and Image Understanding (CVIU), 2022

An Unsupervised Domain Adaptation Scheme for Single-Stage Artwork Recognition in Cultural Sites

Image and Vision Computing (IMAVIS), 2021
View all publications on Google Scholar

Engineering Stack

AI & ML

Python, PyTorch, PyTorch Lightning, TensorFlow, Hugging Face, Scikit-learn, OpenCV, LangChain, LangGraph

Backend & Data

FastAPI, PostgreSQL, MongoDB, Redis, Pandas

DevOps & Tools

Docker, Git, Linux, AWS, CI/CD, MLflow, Jupyter

Other Languages

Java, C++, C#, JavaScript, TypeScript, Flutter

Education

Ph.D. in Computer Science

University of Catania, Italy 2020 — 2023 · Machine Learning, Deep Learning, Computer Vision

M.Sc. in Computer Science

University of Catania, Italy 2018 — 2020 · 110/110 cum laude

B.Sc. in Computer Science

University of Catania, Italy 2015 — 2018 · 110/110 cum laude

Side Projects

agentic-rag-for-dummies

A modular Agentic RAG built with LangGraph — learn and implement Retrieval-Augmented Generation Agents in minutes with multi-agent workflows.

LangGraph Agentic RAG LLMs Python

chunky

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLMs.

RAG FastAPI Chunking Python

DA-Faster-RCNN

Detectron2 implementation of Domain Adaptive Faster R-CNN for Object Detection in the Wild, addressing domain shifts in computer vision (CVPR).

PyTorch Detectron2 Computer Vision Domain Adaptation