Pierre-Loic Doulcet is a Machine Learning Engineer with 14 years of hands-on experience building backend systems and AI solutions from Texas. He combines practical ML engineering with strong backend expertise—evidenced by contributions to the Parsr open-source project where he improved reading-order detection, page number extraction, and PDF robustness. Comfortable navigating messy document data and production constraints, he brings a pragmatic approach to turning unstructured inputs into structured, machine-readable formats. Known for addressing edge cases (like negative PDF widths) and delivering simple, consumable outputs, he bridges research-minded modeling with production-grade engineering.
Transforms PDF, Documents and Images into Enriched Structured Data
Role in this project:
Back-end Developer
Contributions:4 reviews, 19 commits, 20 PRs in 3 years 2 months
Contributions summary:Pierre-Loic primarily contributed to the `parsr` repository by implementing and enhancing back-end modules. They focused on improving the reading order detection algorithm by adding a minimum column width option. Additionally, they added a page number detection module and made improvements to line break detection. The user also introduced a simple JSON output format and addressed code issues, including those arising from negative widths in PDF processing.
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.