Mohamed Filali
Développeur PHP at Treezor - Enable Creative Banking
New York, New York, France
Summary
👤
Senior🎓
Top SchoolMohamed Filali is a seasoned PHP developer with a decade of experience building web and data-driven applications, currently shaping banking platforms at Treezor in New York. He combines backend expertise (PHP, MySQL, Symfony) with a strong bioinformatics and machine learning background from master's studies and R&D work on genomic comparison algorithms. At CEA he led development teams, enforced secure development practices, and drove architecture and code quality across multi-platform projects. An active open-source contributor, he has improved core ML tooling—contributing to MLBox and scikit-learn documentation—bringing practical AutoML and metric clarity to the community. Comfortable moving between research code (Python/Jupyter) and production systems, he thrives on connecting biological data problems with scalable software engineering.
9 years of coding experience
5 years of employment as a software developer
Bachelor's degree, Computer science, Bachelor's degree, Computer science at Polydisciplinary Faculty of SafiMaster's degree, Bioinformatics, Master's degree, Bioinformatics at National School of Computer Science and Systems Analysis - ENSIAS & Faculty of Medicine and Pharmacy of Rabat
Github Skills (18)
python10
data-science10
scikit10
machine-learning10
data-preprocessing10
categorical10
automl10
scikit-learn10
data-analysis10
statistics9
documentation9
automated-machine-learning8
deep-learning8
keras8
encoding8
Programming languages (5)
Github contributions (5)
scikit-learn/scikit-learn
Oct 2017 - Jan 2020
scikit-learn: machine learning in Python
Role in this project:
Data Scientist
Data ScientistContributions:8 commits, 15 PRs, 64 comments in 2 years 3 months
Contributions summary:Mohamed contributed to the documentation of the `scikit-learn` library, specifically focusing on the definition and explanation of multiclass balanced accuracy metrics. Their commits involved adding references, clarifying definitions, and providing examples related to macro-average recall. They also updated the documentation related to the `make_blobs` function and dataset loading, demonstrating an understanding of the library's internal workings and user-facing documentation.
data-analysispythonstatisticsdata-sciencelearn-machine-learning
AxeldeRomblay/MLBox
Jul 2017 - Aug 2017
MLBox is a powerful Automated Machine Learning python library.
Role in this project:Data Scientist
Data ScientistContributions:14 commits, 2 PRs, 23 comments in 8 days
Contributions summary:Mohamed primarily contributed to the `mlbox` library, focusing on the `categorical_encoder` and `na_encoder` modules. Their work involved addressing pep8 issues, refactoring code, adding auxiliary functions, and modifying the entity embedding strategy. They also made changes to the `optimiser` and `predictor` modules, demonstrating a focus on automated machine learning pipelines and model training processes.
kagglexgboostfairness-mlpythonlightgbm
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.