DAVIDE MODOLO
AI Systems Graduate • Computer Vision • Natural Language Processing • Deep Learning • Machine Learning
Passionate about exploring all aspects of Artificial Intelligence - from computer vision to natural language processing with deep learning and classical machine learning.
Eager to apply my knowledge in real-world scenarios and continue growing in this field.
Hire me!
Professional Experience
AI Engineer Intern
Eurecat Technology Center | Barcelona, Spain | April 2024 - June 2024
Explored log-probability-based uncertainty of Large Language Models (LLMs) applied to planning and choice-selection. Developed approaches using GPT 3.5, GPT 4o, and Llama 3.1, creating CSV-based preference collections with RAG to reduce uncertainty in recurrent tasks.
Android App Developer Intern
University of Trento | Trento, Italy | January 2021 - May 2021
Rebuilt a modular Android 11 app for tracking healthy habits using Kotlin and Firebase. Implemented Google login, NoSQL storage, and designed 23+ UI screens with future extensibility features.
Educational Background
Master's Degree in Artificial Intelligence Systems
University of Trento | Trento, Italy | September 2021 - March 2025
Thesis: "Exploring the Use of LLMs for Agent Planning: Strengths and Weaknesses" - Research on Large Language Models applied to automated planning and decision-making scenarios.
Bachelor's Degree in Computer Science
University of Trento | Trento, Italy | September 2017 - June 2021
Thesis: "Healthy Plus - Redesign and evolution of an Android application for monitoring healthy lifestyles" - Complete redesign and modular development of a health tracking mobile application.
Featured Projects
COVID-19 Lung Ultrasound Images Classification
Designed a multi-stage deep learning model to classify Lung Ultrasound images based on a 0-to-3 illness score. Developed 3 components: multi-class frame classifier, uncertainty detection model, and similarity module using 47k frames from 14 real patients.
Joint Intent Detection and Slot Filling - NLU
Implemented 4 Deep Learning models for simultaneous Intent Detection and Slot Filling tasks. Achieved 13% improvement on SNIPS dataset in slot filling task. Fine-tuned BERT and ERNIE, built Bidirectional LSTM and Encoder-Decoder models from scratch.
Domain Adaptation / Transfer Learning
Built and evaluated a deep learning model for Unsupervised Domain Adaptation using ResNet34 with custom adaptation layer. Achieved +11.53% improvement over baseline non-adapted model on Adaptiope dataset using 3rd and 4th-order statistics.
Autonomous Delivery BDI Agent
Designed autonomous agent solution for delivery problems using Belief-Desire-Intent framework. Developed and tested both single-agent and collaborative multi-agent environments across 7 challenges with 2 different approaches.
Parallel Closest Pair of Points - High Performance Computing
Provided a solution to Closest Pair of Points problem in N dimensions with parallel implementation. Implemented both Bruteforce and Divide et Impera solutions using Message Passing Interface (MPI) in C. Tested with up to 250M points using 1 to 80 CPU cores in 4 different configurations on the University's cluster.
Interactive Projects
Digit Classifier
Convolutional Neural Network Digit Recognition
Trained on MNIST dataset using TensorFlow.js. Draw digits clearly in the center.
Sentiment Analysis
AI Sentiment Analysis
Analyzes text sentiment from 0 (negative) to 1 (positive) using ml5.js.