Selected work,
across four years.
A curated selection of production systems, open-source models, and applied research. Most client work is under NDA — described here with anonymized details and verifiable outcomes.
Cloud-native news chatbot
Real-time news summarization for one of Italy's major digital outlets. Multi-agent architecture with persistent memory, streaming responses, and semantic retrieval over a live corpus.
client engagements and applied work
LLM-powered computer vision classifier for automatic CAD parts recognition. Streamlines design workflows for an industrial client by automating part identification and metadata enrichment.
LLM-powered scanning system for receipts and invoices. Enables semantic search across large archives and automated structured data extraction for finance teams.
Cloud-native AI assistant integrated into this website. Provides accurate, context-aware information about my work using multi-agent reasoning, persistent memory, and Gemini/LLM orchestration.
Fine-tuned BERT for personal data detection, deployed into a B2B production platform.
Oracle → PostgreSQL migration with full ETL rewrite on Airflow and CI/CD pipeline.
Real-time cost control dashboard for logistics operations with ML-based anomaly detection on shipment data. Surfaces outliers and pricing irregularities automatically.
ML-based prioritization system integrated into a B2B platform. Ranks incoming orders by urgency and downstream impact, accelerating processing for time-critical requests.
Deep learning classifier for metastatic tissue in lymph node scans. Public on HuggingFace.
GPT-2 fine-tuned on Divina Commedia to generate text in Dante's poetic style and themes.
published on HuggingFace Hub
Deep learning classifier for metastatic tissue detection on lymph node histopathology scans. Kaggle competition baseline.
GPT-2 fine-tuned on the Divina Commedia to generate text in Dante Alighieri's poetic style and themes.
Fine-tuned BERT for misogyny detection in Italian text. Identifies misogynistic content with binary classification.
Custom multimodal agent on the GAIA benchmark, built during the HuggingFace Agents Course — Certificate of Excellence.
Let's see if I'm a fit.
Most of these projects started with a 30-min technical chat. Bring your problem, your stack, and your constraints — I'll come prepared.