Maksim Kuprashevich
Computer Vision Team Leader at Salute Dev
Belgrade, Central Serbia
Summary
👤
Senior🎓
Top SchoolMaksim Kuprashevich is a Computer Vision Team Leader with 12 years of engineering experience and a decade building and scaling production ML systems, currently driving R&D in vision neural networks, multimodal LLMs, and diffusion models from Belgrade. He has led cross-functional teams at Salute Dev, SberDevices and Lanit-Tercom, moving research into deployable services and developer-layer infrastructure. His background spans low-level C++ and kernel work to mobile ADAS solutions and high-level deep learning, reflecting uncommon fluency across the stack. Maksim also contributes to bioinformatics tooling—adding performance-oriented features to the SPAdes genome assembler—illustrating a knack for applying ML and systems thinking to scientific problems. He pairs a strong academic foundation in bioinformatics and computer engineering with a proven track record of shipping reliable, production-focused ML products.
12 years of coding experience
5 years of employment as a software developer
Bachelors, Computer Engineering, 4.8, Bachelors, Computer Engineering, 4.8 at Saint Petersburg State Institute of Technology (Technical University)Advanced Training, Biomathematics, Bioinformatics, and Computational Biology, Advanced Training, Biomathematics, Bioinformatics, and Computational Biology at Bioinformatics Institute
Github Skills (7)
sequencer10
assembly10
c-language10
cprogramming-language10
assemble10
assembler10
genome-assembly10
Programming languages (6)
Github contributions (5)
ablab/spades
Nov 2013 - Mar 2014
SPAdes Genome Assembler
Role in this project:
Backend Developer
Backend DeveloperContributions:7 commits in 4 months
Contributions summary:Maksim implemented new features for the SPAdes genome assembler, including a brute-force cleaning algorithm and a test API, within the C++ codebase. They modified code related to adapter removal and read trimming, crucial for data preprocessing in genome assembly. The commits indicate a focus on optimizing the assembler's performance and incorporating new functionalities, particularly related to read quality analysis and filtering, enhancing the overall accuracy and efficiency of the assembly process.
bioinformaticsgenomeassemblerspadesgenome-assembly
UndeadBlow/PixelAnnotationTool
Aug 2018 - Mar 2020
Contributions:5 releases, 22 pushes, 2 branches in 1 year 6 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.