I am a Senior Data & AI Engineer with experience designing and modernizing data platforms, ETL pipelines, and machine learning workflows.
I specialize in Python, PySpark, Databricks, cloud data engineering, and lakehouse architectures. I have migrated legacy Pandas-based processing to scalable PySpark solutions and delivered substantial performance improvements while reducing cloud operating costs.
I build AI-enabled data products, including agentic AI and multi-agent RAG architectures that allow users to query enterprise data through natural language. My work includes document embedding, vector search, orchestration agents, and integrations with Azure AI Search and PostgreSQL.
I have hands-on experience across AWS and Azure ecosystems, including AWS Glue, S3, Lambda, Kinesis, Athena, Lake Formation, and Databricks. I also use infrastructure and deployment technologies such as Terraform, Docker, and Kubernetes.
My background includes data ingestion, web scraping, streaming, synthetic data generation, business intelligence data preparation, and full-stack development. I hold a Master's degree in Computer Science from the University of Bari.
I led the refactoring of end-to-end ETL processing and machine learning pipelines, migrating legacy Pandas implementations to scalable PySpark workflows.
I implemented an agentic AI solution that enables customers to query data using natural language. The work delivered a 70% performance improvement and reduced cloud operational costs.
Technologies used include Azure, Databricks, Python, Docker, Kubernetes, PostgreSQL, and Terraform.
I developed robust ETL pipelines using AWS Glue to produce clean, aggregated vehicle data for business intelligence dashboards. I worked with AWS CodePipeline, CodeCommit, Lake Formation, Athena, Terraform, and the Glue Data Catalog.
I designed a multi-agent RAG architecture for enhanced data retrieval, including Databricks and PySpark pipelines for document embeddings and vector search. I processed on-premise ticket data into Azure AI Search and PostgreSQL, and deployed a CrewAI orchestrator for unified responses across systems.
I generated synthetic datasets with machine learning models, ingested data into RDS PostgreSQL through AWS Glue, and enabled on-demand synthesis with AWS Lambda. I also streamed synthetic orders through AWS Kinesis for anomaly detection.
I built web-scraping and ingestion workflows using Python, Selenium, Beautiful Soup, Apache Airflow, and Amazon S3, landing data in a Databricks medallion lakehouse for enrichment, processing, and quality assurance.
I contributed to the Fontaninapp project, a multi-platform mobile application for geolocating fountains in Apulia.
Master of Science, Computer Science
Bachelor's degree, Informatics and Technologies for Software Production
This professional hasn’t added portfolio projects yet.
This professional hasn’t listed any services yet.
