Chris Kamphuis
Data Scientist
Oldenzaal, Overijssel, Netherlands
Summary
🤩
Rockstar🎓
Top SchoolChris Kamphuis is a data scientist and PhD candidate at Radboud University with 11 years of experience applying information retrieval and data science techniques to large temporal graphs and search systems. He blends academic rigor—researching IR for temporal graphs—with industry practice as a Data Scientist at Spinque and an Applied Scientist intern on Amazon’s Search Relevance team. Chris is an active back-end contributor to prominent open-source IR toolkits such as Pyserini and Anserini, where he improved query capabilities, analyzer APIs, date filtering, and BM25 behavior to boost reproducibility and performance. With an MSc (cum laude) in Computer Science and a BSc in Artificial Intelligence, he also has hands-on experience in deep learning for medical imaging and mobile image analysis. Known for bridging research and production, he brings a rare combination of tooling work, course instruction, and lab management to practical search and retrieval problems.
11 years of coding experience
2 years of employment as a software developer
Master of Science (MSc), Computer science, Cum Laude, Master of Science (MSc), Computer science, Cum Laude at Radboud Universiteit NijmegenBachelor of Science (BSc), Kunstmatige Intelligentie, Bachelor of Science (BSc), Kunstmatige Intelligentie at Radboud University Nijmegen
Dutch, English
Stackoverflow
467reputation
22kreached
11answers
1question
Github Skills (18)
lucene10
python10
information-retrieval10
java10
javas10
query-parser10
query-engine10
querying10
algorithm9
algorithms9
testing8
api-design8
bubble-sort6
tensorflow6
cross-validation6
Programming languages (5)
Github contributions (5)
castorini/anserini
Nov 2018 - Mar 2021
Anserini is a Lucene toolkit for reproducible information retrieval research
Role in this project:
Back-end Developer
Back-end DeveloperContributions:18 commits, 23 PRs, 36 comments in 2 years 4 months
Contributions summary:Chris primarily contributed to the back-end aspects of the Anserini project, focusing on information retrieval research. They added features such as date filtering to the background linking reranker, enhanced BM25 similarity calculations for improved accuracy, and created utility scripts to extract document lengths. Furthermore, the user made adjustments to the search functionality, including phrase query document frequency calculations, showcasing their understanding of the project's core functionalities. The user also added command line options during indexing and searching.
reproducibleretrievalluceneinformation-retrievaljava
castorini/pyserini
Mar 2020 - Mar 2021
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
Role in this project:Back-end Developer
Back-end DeveloperContributions:4 reviews, 7 commits, 14 PRs in 1 year
Contributions summary:Chris contributed to the Pyserini project by implementing new features and making refactoring changes related to information retrieval research. They added an API for analyzers, allowing users to change analyzers in pysearch, and refactored the codebase according to Anserini changes. Furthermore, the user implemented functionality to build and integrate queries within the searcher to broaden its query capabilities and improve the query performance. These changes suggest contributions towards the core functionality and flexibility of the Pyserini toolkit.
record-linkagepythonrepresentationssparsesimilarity
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.