Tobias聽Pitters
CTO Of Cloudexplain Building Explainable AI For The Cloud at Freelance, self-employed
Munich, Bavaria, Germany
Summary
馃ぉ
Rockstar馃帗
Top SchoolTobias Pitters is a CTO and data science engineer with 8 years of experience building explainable AI and production-ready data systems, currently leading Cloudexplain to make model decisions transparent for cloud customers. He combines a physics-trained analytical mindset with hands-on expertise in Python and Rust, freelancing on data science projects while previously shaping ETL and anomaly-detection frameworks at Telef贸nica and ML solutions at Quantwerker. An active open-source maintainer of shap and contributor to flagship libraries like pandas, NumPy and Polars, he focuses on trustworthy model explanations and robust testing. Notably, his contributions to SHAP鈥檚 TreeExplainer and rigorous test work across scientific stacks reflect a rare blend of research-level rigor and production engineering. Based in Munich, he thrives at the intersection of big data, machine learning, and pragmatic tool-building for trustworthy AI.
8 years of coding experience
4 years of employment as a software developer
Master of Science - MS Physik, Master of Science - MS Physik at University of Stuttgart
Stackoverflow
3,124reputation
114kreached
126answers
2questions
pandas
top-5%
machine-learning
top-5%
python
top-5%
Github Skills (40)
xgboost10
catboost10
shap10
python10
testing10
dataframes10
pandas10
machine-learning10
polar10
numpy10
dataframe10
keras10
explainable-artificial-intelligence10
tensorflow10
polars10
Programming languages (9)
Github contributions (5)
shap/shap
Sep 2023 - Mar 2025
A game theoretic approach to explain the output of any machine learning model.
Role in this project:
ML Engineer
ML EngineerContributions:2 releases, 239 reviews, 126 PRs in 1 year 6 months
Contributions summary:Tobias primarily contributed to the development and improvement of machine learning model explanations within the SHAP library. Their work focused on refining and adapting the TreeExplainer, particularly in scenarios involving tree-based models like XGBoost, LightGBM, and CatBoost. Key contributions include addressing consistency issues, fixing bugs related to interactions, and supporting new features related to the explanation of the models. Additionally, the user worked on incorporating enhancements to support recent developments in the Tensorflow and Keras libraries.
explaininterpretabilityshapdeep-learningapproach
pandas-dev/pandas
Apr 2020 - Aug 2022
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:Data Scientist / QA Engineer
Data Scientist / QA EngineerContributions:28 reviews, 11 commits, 13 PRs in 2 years 4 months
Contributions summary:Tobias contributed to the pandas library by implementing and testing fixes for various data analysis and manipulation functionalities. They addressed bugs related to `groupby`, `interpolate`, and `crosstab` operations, ensuring the library's consistency and correctness. Furthermore, the user added tests and improved the existing test suite to enhance the overall quality and reliability of pandas, covering a range of scenarios. These contributions demonstrate a focus on improving the stability of the library.
pythondatalabeled-datamanipulationdataframes
Find and Hire Top DevelopersWe鈥檝e 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.