Kemal Eren
Computer Vision Research Engineer at Ancera
Greater Cleveland United States
Summary
👤
Senior🎓
Top SchoolKemal Eren is a computer vision research engineer with 16 years of experience building and productionizing ML and imaging systems across startups, healthcare, and robotics. He blends deep academic training (PhD in Bioinformatics from UC San Diego) with hands-on engineering roles—from improving test automation in the widely used Snakemake workflow to implementing biclustering algorithms in scikit-learn. At companies like Bossa Nova Robotics and Ancera he has translated research into robust deployments, while earlier work spans GPU-accelerated sequence mapping and interactive ML tooling for ilastik. Pragmatic and detail-oriented, he often focuses on testability and reproducibility (e.g., fixing brittle tests and adding stochastic-output checks) to make complex models reliable in production. Based in Greater Cleveland, he brings a rare mix of biological data insight and production machine learning expertise.
16 years of coding experience
12 years of employment as a software developer
University of California San DiegoB.S., Biology, B.S., Biology at University of MichiganSt. IgnatiusM.S., Computer Science and Engineering, M.S., Computer Science and Engineering at The Ohio State University
Github Skills (19)
python10
data-science10
testing10
scikit10
machine-learning10
data-serialization10
serialization10
scikit-learn10
workflow-management10
snakemake9
rep9
algorithms9
front-end-development9
repr9
pytest8
Programming languages (8)
Github contributions (5)
scikit-learn/scikit-learn
Apr 2013 - Sep 2013
scikit-learn: machine learning in Python
Role in this project:
Data Scientist
Data ScientistContributions:100 commits in 4 months
Contributions summary:Kemal contributed to the scikit-learn repository by modifying the ridge regression module. Their work involved integrating the `compute_class_weight()` function within `RidgeClassifier`, improving consistency by re-adding the `class_weight` parameter in `RidgeClassifier.fit()` and `RidgeClassifierCV.fit()`, and then removing it from `RidgeClassifier.fit()`. Further contributions included the implementation of spectral biclustering and spectral co-clustering algorithms. They also wrote tests to validate their work.
data-analysispythonstatisticsdata-sciencelearn-machine-learning
ilastik/ilastik
Nov 2012 - Jun 2013
ilastik-shell, applets, and workflows to string them together.
Role in this project:Back-end Developer
Back-end DeveloperContributions:188 commits in 7 months
Contributions summary:Kemal primarily worked on the `ilastik/ilastik` repository by modifying the `layerViewerGui.py` file, adding a new reset axes functionality and adding a conversion function related to the appletSerializer. They also moved slice/string conversion functions to `appletSerializer.py` and fixed unit tests in `pixelClassificationSerializer`. The code differences indicate contributions to improving the GUI for the object workflow and modifications to the serialization and deserialization processes within the application.
to-stringpythonstringilastikmachine-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.