Sara Zanzottera is an Agentic AI Lead with 11 years of engineering experience building production-grade NLP and autonomous agent systems across research labs and finance. She combines deep Python expertise with hands-on work in GenAI orchestration—contributing to deepset’s popular Haystack project by improving FAISS document store persistence and REST integrations. Her career spans CERN instrumentation software, large-scale on-prem LLM deployments at BNP Paribas CIB, and leading development of autonomous voice agents for recruitment at Kwal. Comfortable from embedded solar-powered Raspberry Pi systems to enterprise-compliant stacks, she focuses on robust, auditable pipelines for data-sensitive environments. A sci-fi reader who studies unusual languages, she brings curiosity and interdisciplinary thinking to complex AI product problems. Based in Portugal, she blends open-source contribution with practical leadership to move ML innovations into production.
11 years of coding experience
10 years of employment as a software developer
Bachelor's degree Computer Engineering, Bachelor's degree Computer Engineering at Tongji University
Master's Degree Data Science (Big Data), Master's Degree Data Science (Big Data) at Politecnico di Milano
Master's Degree Data Science (Big Data), Master's Degree Data Science (Big Data) at Université Côte d'Azur
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
Role in this project:
Back-end Developer
Contributions:7 releases, 1538 reviews, 552 commits in 1 year 4 months
Contributions summary:Sara's contributions centered on improving the save/load functionality of the FAISS document store, including saving and loading its configuration alongside the index. This involved modifications to the underlying code to persist and restore initialization parameters, as well as implementing tests to verify the integrity of the loading process. Additional contributions include fixing bugs and making adjustments to the rest API.
:mag: Haystack is an open source NLP framework that leverages Transformer models. It enables developers to implement production-ready neural search, question answering, semantic document search and summarization for a wide range of applications.
Contributions:3 PRs, 34 pushes, 8 branches in 1 year 9 months
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.