PhD Student in Artificial Intelligence for Society at the University of Messina and the University of Pisa. I received my MSc in Data Science in 2025 and my BSc in Computer Science in 2023 from the University of Messina, where I also served as a research fellow working on Smart Cities and Smart Mobility projects, particularly focusing on the design and development of a mobile application for local public transportation.

My research later evolved toward Machine Learning optimization techniques, emphasizing model compression, pruning, and distributed intelligence within cloud–edge continuum architectures. I have worked on approaches to reduce the computational and memory footprint of neural networks while preserving predictive accuracy, enabling efficient deployment of AI models in resource-constrained environments such as edge nodes and IoT infrastructures. In 2025, this line of research was funded by the European project Neurokit2E, which supported my investigations into efficient neural computation, adaptive inference strategies, and context-aware model distribution for next-generation distributed AI ecosystems.

My current research is focused into the development of Function-as-a-Service (FaaS) architectures, cloud-edge metrics forecasting, and anomaly detection within distributed and resource-constrained environments. Specifically, I focus on spatio-temporal Transformer models capable of learning complex dependencies across heterogeneous telemetry data—such as CPU, GPU, and memory utilization—collected from multi-tenant cloud and edge infrastructures. These models aim to predict system behavior, detect emerging anomalies in real time, and optimize resource allocation dynamically. This research connects deeply with my broader interest in distributed intelligence, seeking to enhance scalability, adaptability, and energy efficiency in serverless AI pipelines.

Meanwhile, my research extends into the integration of blockchain and AI, exploring innovative mechanisms for data certification, provenance tracking, and transparency in machine-generated processes. The goal is to establish trustworthy AI pipelines where every stage—from data collection to model inference—is cryptographically verifiable and ethically accountable. In parallel, I conduct research and development with Circular Protocol, focusing on the creation of decentralized infrastructures for digital manufacturing and pharmaceutical certification. Within this collaboration, I investigate blockchain-based mechanisms for ensuring regulatory compliance, traceability of industrial data, and integrity of AI-assisted decision systems.

My research interests span machine learning optimization, trustworthy AI, blockchain for data integrity, and cloud-edge intelligence architectures.

Passionate about Artificial Intelligence and Blockchain technologies, I am driven by the goal of integrating trust, transparency, and verifiability into data-driven processes, exploring how decentralized infrastructures can enhance accountability in AI systems beyond their traditional financial applications.

My research activities focus on the intersection of Machine Learning optimization, blockchain-based data certification, and trustworthy AI, with applications ranging from cloud-edge intelligence to digital manufacturing and pharmaceutical process certification.