Ilya Churaev is a Lead Software Engineer with 11 years of experience specializing in C++ and AI/ML inference frameworks. He spent a decade at Intel advancing nGraph/OpenVINO and deep integration with OpenCV’s DNN module, contributing to production-grade support for ONNX operators, quantization, and float16 optimizations. Currently leading engineering at Sberbank, he combines low-level systems expertise with practical ML deployment patterns to drive performant inference pipelines. Ilya holds a Master’s in Applied Mathematics and Informatics from HSE, underpinning his work with strong algorithmic and numerical foundations. Notably, his open-source contributions to widely used projects like OpenVINO and OpenCV reflect a focus on compatibility and performance across runtimes and hardware. He’s the kind of engineer who moves seamlessly between core library fixes and deployment-facing features, ensuring research models run reliably in production.
11 years of coding experience
9 years of employment as a software developer
Master’s Degree, Applied Mathematics and Informatics, Master’s Degree, Applied Mathematics and Informatics at Higher School of Economics
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & ML Engineer
Contributions:5780 reviews, 508 commits, 2221 PRs in 2 years 8 months
Contributions summary:Ilya's commits primarily revolve around modifying and updating the OpenVINO toolkit, a repository focused on optimizing and deploying AI inference. Contributions include changes to core functionalities like the ngraph public API, file utilities, and type handling. The user demonstrates involvement in machine learning by modifying and implementing support for ONNX operators as well as for Quantization methods.
nGraph - open source C++ library, compiler and runtime for Deep Learning
Role in this project:
Back-end Developer & ML Engineer
Contributions:54 commits, 64 PRs, 80 pushes in 11 months
Contributions summary:Ilya contributed to the nGraph library by implementing and fixing features related to deep learning operations. They added support for float16 data types, fixed builds, and addressed issues in the reference broadcast implementation. Their work also included modifications to the function specialization process and the handling of runtime information, impacting the core functionality of the library. The user also made changes to the Python build process and the NonMaxSuppression operation.
inference-enginecppc-librarydeep-learningtvm
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.