Semion Sidorenko
Lead Data Engineer
Lausanne, Vaud, Switzerland
Summary
👤
Senior🎓
Top SchoolSemion Sidorenko is a Lead Data Engineer based in Lausanne with 13 years of experience delivering production-grade data platforms and ML-enabled applications across public sector and research environments. He combines deep hands-on expertise in Python, PostgreSQL, PyTorch and scalable infra with proven leadership—having scaled an engineering team and multiplied contact-tracing capacity during the COVID response. As a doctoral researcher at EPFL he brings an uncommon sociological lens to how digital data is produced and used in public administrations, bridging ethnography with engineering. His open-source contributions include improving superpixel segmentation and uncertainty visualization in ilastik, reflecting a knack for making research tools performant and user-friendly. Known for turning prototypes into resilient services, he moves fluidly between low-level ML optimization and high-level data-product strategy.
13 years of coding experience
10 years of employment as a software developer
Maturité fédérale option physique/maths, Maturité fédérale option physique/maths at Gymnase d'YverdonBachelor of Arts - BA Social Sciences, Bachelor of Arts - BA Social Sciences at University of Lausanne - UNILMaster of Science (M.Sc.) Computer Science, Master of Science (M.Sc.) Computer Science at EPFL
Stackoverflow
140reputation
18kreached
6answers
4questions
Github Skills (13)
computer-vision10
machine-learning10
scikit-image10
python10
numpy9
qt9
ls6
licensing6
linux6
django-rest-framework6
scalajs6
django6
django-templates6
Programming languages (11)
Github contributions (5)
ilastik/ilastik
Mar 2017 - Jan 2018
ilastik-shell, applets, and workflows to string them together.
Role in this project:
ML Engineer
ML EngineerContributions:19 commits, 2 PRs, 1 comment in 10 months
Contributions summary:Semion contributed to the development of a SLIC superpixel applet within the voxel segmentation workflow. They implemented caching for the SLIC segmentation results to improve performance and also included changes for showing the top uncertain regions. These changes involved modifications to existing Python files, including the creation of a new GUI element for the SLIC visualization and also the introduction of functions to handle the supervoxel calculations. These enhancements aimed to integrate superpixel segmentation into the project's machine learning pipelines.
to-stringpythonstringilastikmachine-learning
ssidorenko/dotfiles
Mar 2019 - Oct 2022
Contributions:22 pushes, 1 branch in 3 years 7 months
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.