Nice to meet you! 
I'm Matteo Fasulo, an AI Engineer with a strong focus on Machine Learning, Deep Learning, and Generative AI.I hold a BSc in Computer Science and a MSc in Artificial Intelligence.
My work spans both research and applied projects across multiple AI domains, including Large Language Models, NLP, Biosignal modeling, and Embedded AI systems. I have hands-on experience with self-supervised learning, transformer-based architectures, prompt-based evaluation, and retrieval-augmented methods, developed through academic research, collaborations, and open-source contributions.
- Biosignal Modeling - TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge
- NLP (CLEF 2025) - Enhancing Transformer-Based Embeddings with Sentiment for Subjectivity Detection in News Articles.
- Generative AI & LLMs - Prompt-based evaluation, in-context learning, and retrieval-augmented generation. Mainly conducted at Outlier AI.
- NLP (EXIST 2023) - EXIST 2023 task in finetuning models for Sexism Detection in Social Media and EDOS task from SemEval 2023 using In-Context Learning with zero-shot and few-shot learning. https://github.com/MatteoFasulo/Sexism-detection
- Embedded AI - Low-level optimization and implementation on Xilinx/Versal VCK190. https://github.com/MatteoFasulo/Versal-C-Code
- Data Mining - Amazon review sentiment analysis using R Shiny, ggplot, Plotly, and text mining pipelines.
- Cloud Computing - Scalable WebApp using Docker Swarm, Ansible, ShinyProxy, Traefik, InfluxDB, and Grafana monitoring. https://github.com/MatteoFasulo/ScalableWebApp
Some experience (and occasionally, contribution) worth to mention over open source projects:
- OpenAI Whisper under HuggingFace transformer.js with ONNX Runtime and WebGPU.
- Adversarial Robustness Toolbox (ART) hosted by Linux Foundation AI & Data Foundation (LF AI & Data).
- pgmpy library for Bayesian Networks.
- Whisper-TikTok – A side project I started purely for fun: an AI-driven tool with Microsoft Edge TTS, OpenAI Whisper, and FFmpeg to automatically generate TikTok-style videos—with transcriptions, voiceovers, and background content—just by tweaking a simple JSON file.
