Roberto Esposito
Research Engineer at Weaviate
Oregon, Italy
Summary
🤩
Rockstar🎓
Top SchoolRoberto Esposito is a research-focused software engineer with five years of experience building memory- and performance-conscious systems for AI and search. Currently a Research Engineer at Weaviate and working with Oracle, he has contributed to the open-source Weaviate vector database by improving metrics, memory estimation, and robustness around node failures. His research background includes quantization-driven K-NN indexes in Rust that cut memory use by up to 90% and a measurable 30% Faiss performance gain, plus FPGA and RTOS cryptography work at Leonardo. Comfortable across back-end systems, low-level optimization, and production ML infrastructure, he specializes in teaching AI models to “remember” efficiently through multi-vector encodings and model-specific quantization. Trained with honors at Università di Pisa and Salerno, he blends academic rigor with pragmatic engineering and a knack for squeezing large gains from careful systems design.
5 years of coding experience
4 years of employment as a software developer
Bachelor's degree, Computer Science, 110 with honors, Bachelor's degree, Computer Science, 110 with honors at Università degli Studi di SalernoMaster's degree, Computer Science, 110 with honors, Master's degree, Computer Science, 110 with honors at Università di Pisa
Italian, English, Spanish
Github Skills (6)
vector-search10
vector-database10
go10
metric10
testing9
hnswlib9
Programming languages (7)
Github contributions (5)
weaviate/weaviate
Sep 2023 - Apr 2025
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:23 reviews, 46 PRs, 156 pushes in 1 year 6 months
Contributions summary:Roberto primarily contributed to adding new metrics, and enhancing the existing ones, for batch sizes and object processing in Weaviate. They also added functionality related to a fixed seed vector generator function and modified existing testing helpers. The user further implemented code that estimates the object memory consumption and fixed a bug that would arise from a deleted node during a search. These changes focus on improving data handling, memory management, and testing within the vector database.
approximate-nearest-neighbor-searchsemantic-search-enginehnswfaultsimilarity-search
robbespo00/information-retrieval-notes
Dec 2021 - Jan 2022
Contributions:10 commits, 8 pushes, 1 branch in 25 days
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.