Henning Sperr is a Senior Machine Learning Engineer with 13 years of experience building production ML systems across startups and large enterprises, currently driving ML efforts at Mercari in Hokkaido. He combines hands-on modeling (XGBoost, deep learning, graph algorithms) with pragmatic product delivery—favoring simple, deployable solutions that evolve into robust pipelines. At Zalando he co-led an 8-person team to design fraud detection that replaced manual screening and owned OKRs influencing company direction, and at Paidy he built credit and fraud stacks from scratch for high-throughput finance use cases. Comfortable across the data stack (Python/Scala, Spark/Databricks, SQL/NoSQL) he also contributes QA-focused tests to major open-source projects like pandas, underscoring a commitment to reliability. He excels at translating technical insights into clear KPIs and stakeholder-facing reports, believing the right tool for the audience is as important as model performance. Colleagues know him as a pragmatic leader who scales teams and processes so engineers and data scientists can deliver quickly and confidently.
13 years of coding experience
14 years of employment as a software developer
Diplom Informatiker, Informatik, Diplom Informatiker, Informatik at Universität Karlsruhe (TH)
Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
Role in this project:
QA Engineer / Test Automation Engineer
Contributions:5 commits, 5 PRs, 14 comments in 3 months
Contributions summary:Henning primarily contributed to the testing and quality assurance aspects of the pandas library. Their commits focused on adding tests for new functionalities, ensuring existing features behaved as expected, and addressing reported issues. Specific changes included adding tests for file path expansion, decimal division, and the index name in time series resampling, and also covering other relevant code changes. These tests ensure the library's reliability and maintainability by validating correct behavior.
Contributions:27 commits, 2 PRs, 16 pushes in 8 months
helpersmachine-learning
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.