Levi Borodenko
Software Engineer at Smart Steel Technologies
Berlin, Germany
Summary
👤
Senior🎓
Top SchoolLevi Borodenko is a Berlin-based software engineer with nine years of experience specializing in data science and database administration, currently delivering process optimisations for large-scale steel plants at Smart Steel Technologies. He holds first-class degrees in Mathematics and Statistics from the University of Oxford and applies strong mathematical rigor to practical engineering problems. An active contributor to open-source ML tooling, he has implemented advanced Graph Neural Network layers (SortPool, DiffusionConvolution) and batch operations in the spektral library, showing both research-grade understanding and production-minded engineering. His background includes statistical research for the German Federal Bureau of Statistics and large-team leadership in education programs, reflecting an ability to translate complex analytics into operational solutions. Quietly technical and detail-oriented, he blends theory, data engineering, and software craftsmanship to improve industrial-scale processes.
9 years of coding experience
Bachelor's degree, Mathematics and Statistics, GPA: 3.9, Bachelor's degree, Mathematics and Statistics, GPA: 3.9 at University of Oxford
German, English, Russian
Github Skills (7)
keras10
deep-learning10
tensorflow10
graph-neural-network10
python10
develop9
testing8
Programming languages (4)
Github contributions (5)
danielegrattarola/spektral
Apr 2020 - May 2020
Graph Neural Networks with Keras and Tensorflow 2.
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:20 commits, 5 PRs, 15 comments in 25 days
Contributions summary:Levi primarily contributed to the implementation of a new layer, `SortPool`, within the `spektral` library, demonstrating proficiency in graph neural network architectures. They also integrated this layer into the testing framework and updated the documentation, showcasing skills in software development and documentation. Furthermore, the user introduced the `DiffusionConvolution` layer, enhancing the library's capabilities, and they developed the `disjoint_to_batch` operation.
pythondeep-learninggraph-deep-learningneural-graphneural-networks
LeviBorodenko/primify
Jul 2019 - Jan 2022
Embed any image into a prime number.
Contributions:33 commits, 1 PR, 30 pushes in 2 years 6 months
pythondigitmathematicsprimeimage-processing
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.