Nicola Procopio is a Senior Data & AI Scientist with a decade of experience applying machine learning, statistics and graph analysis to real-world products and research. He has led data science teams and R&D initiatives across healthcare, enterprise and innovation hubs, specializing in semantic search, NLU, vector databases and LLM-driven retrieval applications. An active open-source contributor, Nicola has contributed hybrid search, embedding and document-processing enhancements to the widely used Haystack framework, improving retrieval performance and pipeline robustness. He blends rigorous academic training—an Applied Statistics master's with magna cum laude—with hands-on engineering, from ETL and GIS to production-ready AI modules. Based in Calabria, Italy, he combines dissemination and advocacy with pragmatic product delivery, and is known for translating graph-theory and social-network analysis insights into scalable ML solutions.
10 years of coding experience
14 years of employment as a software developer
Master's degree, Applied Statistics, magna cum laude, Master's degree, Applied Statistics, magna cum laude at Università degli Studi della Calabria
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
Role in this project:
ML Engineer
Contributions:5 reviews, 9 PRs, 30 comments in 2 years 6 months
Contributions summary:Nicola primarily contributed to the development and enhancement of the Haystack framework, focusing on features related to hybrid search, embeddings, and document processing. They implemented examples and pipelines demonstrating hybrid search capabilities and improved existing examples. Furthermore, they added functionalities such as dimension parameters for Azure OpenAI embedders and distribution-based rank fusion, demonstrating a focus on improving retrieval methods and performance. The user also fixed bugs and refactored code related to join operations and document splitting within the framework.
A python library for unsupervised time series analysis
Contributions:4 releases, 3 reviews, 115 commits in 8 months
pythontime-seriesunsupervised-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.