Peter Staar
Principal Research Staff Member, Master Inventor, Manager Of AI For Knowledge Group at The Linux Foundation
Zurich, Zurich, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolPeter Staar is a Principal Research Staff Member and Master Inventor leading IBM’s "AI for Knowledge" group in Zurich, where he builds the Deep Search platform and applies state-of-the-art AI for document understanding and large-scale knowledge extraction. With a strong research background (PhD and postdoc work at ETH Zürich) and hands-on leadership of cloud-native knowledge ingestion platforms, he bridges advanced research and production deployments across multi-cloud environments. He chairs the Docling technical steering committee at the Linux Foundation for AI and Data and contributes to the popular docling open-source project, focusing on test automation and robust document-to-AI pipelines. Known for combining high-performance computing instincts with practical engineering, he designs systems that turn complex documents and streaming data into scalable knowledge graphs.
4 years of coding experience
3 years of employment as a software developer
Bachelor of Applied Science - BASc, Theoretical and Mathematical Physics, Bachelor of Applied Science - BASc, Theoretical and Mathematical Physics at KU LeuvenMaster of Science (M.Sc.), Physics, Master of Science (M.Sc.), Physics at ETH Zürich
Dutch, English, French, German
Github Skills (23)
unit-testing10
pytest10
python10
markdown9
json9
document-processing9
parsing9
parse9
markdown-it9
datatables8
temp-tables8
pdf7
ai7
pdf-conversion5
html5
Programming languages (6)
Github contributions (5)
docling-project/docling
Jul 2024 - Mar 2025
Get your documents ready for gen AI
Role in this project:
QA Engineer / Test Automation Engineer
QA Engineer / Test Automation EngineerContributions:139 reviews, 41 PRs, 113 pushes in 8 months
Contributions summary:Peter's primary contributions revolve around implementing and enhancing unit tests within the `docling` project. They added comprehensive tests, including those for JSON and Markdown outputs and back-end functions. Furthermore, the user refactored code and addressed backend testing issues, ensuring code quality and stability. Their work included verifying the correct output by asserting that data structures match.
aiconvertdocument-parserdocument-parsingdocx
docling-project/docling-parse
Aug 2024 - Mar 2025
Simple package to extract text with coordinates from programmatic PDFs
Contributions:37 reviews, 60 PRs, 183 pushes in 7 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.