Karlson Pfannschmidt
Co-Founder at Paderborn University
Paderborn, North Rhine-Westphalia, Germany
Summary
🤩
Rockstar🎓
Top SchoolKarlson Pfannschmidt is a machine learning researcher and entrepreneur with 18 years of technical experience and a decade focused on ML, information retrieval and NLP. As co-founder of Puraite and a researcher at Paderborn University, he is building tools to deliver consolidated, evidence-based medical answers to policymakers and pharma in real time. His PhD work covered preference learning, extreme multi-label classification, Gaussian processes and bandits, giving him deep expertise in probabilistic modeling and decision-making under uncertainty. Karlson has contributed to notable open-source projects like PyMC—adding priors and fixing core distribution issues—and has backend experience extending the BWAPI game API, reflecting both statistical depth and systems-level pragmatism. A Startup School alumnus who won the final pitch with Puraite, he combines academic rigor with product-minded execution. Based in Paderborn, Germany, he is particularly interested in collaborations that translate research-grade models into actionable healthcare intelligence.
17 years of coding experience
4 years of employment as a software developer
Master of Science (M.S.), Computer Science, Master of Science (M.S.), Computer Science at Universität Paderborn / University of Paderborn
German, English
Stackoverflow
413reputation
10kreached
3answers
1question
Github Skills (18)
c-language10
probabilistic-programming10
python10
statistics10
statistic10
mcmc10
pymc10
bayesian10
game-development10
cprogramming-language10
bayesian-inference10
numpy9
apidoc9
object-oriented-programming9
theano9
Programming languages (7)
Github contributions (5)
bwapi/bwapi
May 2008 - Jul 2009
Brood War API
Role in this project:
Back-end Developer
Back-end DeveloperContributions:50 commits in 1 year 1 month
Contributions summary:Karlson implemented and refactored core game logic functions within the Brood War API (BWAPI) project, including functions for checking game state, screen output, and player resource management. They extended the API with new functionalities like unit movement, attack control, and tech/building commands. Furthermore, the user added methods for status timer retrieval, focusing on gameplay data access and control within the StarCraft environment.
starcraftapigamebwapibroodwar
pymc-devs/pymc
Feb 2015 - Jul 2016
Bayesian Modeling and Probabilistic Programming in Python
Role in this project:Data Scientist
Data ScientistContributions:15 commits, 8 PRs, 41 comments in 1 year 5 months
Contributions summary:Karlson primarily contributed to the development and improvement of Bayesian modeling capabilities within the PyMC repository. Their work included fixing errors in distributions such as the Wishart and MvNormal, ensuring correct parameter ordering and handling of multiple observations. The user also introduced the LKJ prior for correlation matrices, added example code, and updated the unit tests. These contributions enhance the statistical and probabilistic programming capabilities of the library.
pythonbayesian-inferencestatistical-inferencemachine-learningprobabilistic-programming
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.