Panos Vagenas
Advisory Software Engineer (Band 8), Data & AI Platforms
Zurich, Zurich, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolPanos Vagenas is an advisory software engineer based in Zurich with over a decade of experience building Data & AI platforms and mission-critical systems, currently driving platform strategy and delivery at IBM. He progressed through senior engineering bands at IBM after earlier roles in Swiss consulting where he combined solution architecture, client-facing leadership and hands-on development across Java, Python and data stacks. Panos contributes to open-source tooling for document preparation for generative AI as a back-end developer on the docling project, improving conversion workflows and data models to streamline document-to-AI pipelines. His background includes research on temporal queries for SAP HANA and an ETH Zurich MS in Computer Science, reflecting a blend of systems-level research and practical production engineering. Colleagues describe him as a pragmatic architect who turns complex data-processing requirements into reliable, maintainable platforms.
6 years of coding experience
Bachelor's degree, Informatics and Telecommunications, Bachelor's degree, Informatics and Telecommunications at National & Kapodistrian University of AthensMaster of Science - MS, Computer Science, Master of Science - MS, Computer Science at ETH Zurich
English, German, Spanish, French, Greek
Github Skills (20)
python10
data-modeling10
document-conversion10
markdown9
markdown-it9
ppx8
file-converter8
pdfa8
html8
ledger-tables8
image-converter8
datatables8
temp-tables8
ai8
docx8
Programming languages (4)
Github contributions (5)
docling-project/docling
Jul 2024 - Apr 2025
Get your documents ready for gen AI
Role in this project:
Back-end Developer
Back-end DeveloperContributions:81 reviews, 132 PRs, 143 pushes in 8 months
Contributions summary:Panos primarily focused on enhancing the `docling-project/docling` repository by integrating core functionalities and improving document conversion processes. They switched to using the `docling-core` Markdown export, added support for single-document conversion, and corrected page numbering in the data model. Furthermore, the user introduced and refined `ConversionResult` and `ConvertedDocument` and their related elements, suggesting a deep dive into conversion workflows. These changes indicate a focus on improving data handling and streamlining the conversion process.
aiconvertdocument-parserdocument-parsingdocx
vagenas/deepsearch-toolkit
Oct 2022 - Jul 2023
Interact with the DeepSearch platform for new knowledge explorations and discoveries
Contributions:25 releases, 91 pushes, 32 tags in 9 months
knowledgeinteractdiscoveriesexplorations
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.