Sergey Shalnov
AI Software Solutions Engineer at Intel Corporation
Warsaw, Masovian Voivodeship, Poland
Summary
🤩
Rockstar🎓
Top SchoolSergey Shalnov is an AI software solutions engineer with 10+ years of experience architecting and delivering high-performance computing and machine learning runtimes, currently leading AI software efforts at Intel in Warsaw. He combines deep compiler and low-level systems expertise—contributing to projects like nGraph, clDNN and Numba—with hands-on work exposing Intel GPU acceleration to Python ecosystems such as NumPy and Data Parallel NumPy. A proven technical leader, Sergey has driven full lifecycle projects, optimized GCC vectorization and AVX512 codegen, and shipped Intel ONE API components while managing cross-functional teams. His open-source contributions include implementing core deep-learning backends and Unicode string operations in widely used projects, reflecting both breadth and attention to detail. Notably, he blends hardware-aware optimizations with practical Python integration, enabling real-world ML workloads to leverage Intel architectures.
9 years of coding experience
24 years of employment as a software developer
Master of Computer Science in Information and Communication Technologies and Communication Systems, Information and Communication Technologies and Communication Systems, Master of Computer Science in Information and Communication Technologies and Communication Systems, Information and Communication Technologies and Communication Systems at Nizhny Novgorod State Technical University
English, Russian, poland
Github Skills (24)
opencl10
activation-function10
c-language10
back-end-development10
python10
gpu-programming10
compiler-compiler10
deep-learning10
deep-neural-networks10
compiler10
numba10
backend10
cprogramming-language10
testing9
numpy9
Programming languages (5)
Github contributions (5)
NervanaSystems/ngraph
Jun 2018 - May 2019
nGraph - open source C++ library, compiler and runtime for Deep Learning
Role in this project:
Back-end Developer
Back-end DeveloperContributions:124 commits, 116 PRs, 230 pushes in 10 months
Contributions summary:Sergey primarily focused on implementing the IntelGPU backend for the nGraph deep learning compiler. Their contributions include the initial setup and implementation of an IntelGPU backend utilizing clDNN, along with the addition of core operations such as addition, multiplication, division, maximum, minimum, constant, negative, Relu, and others to the compile method for the IntelGPU backend. They developed code to support various operations, including BatchNorm and also began work on a Dot operation, and improved existing functionality such as the Broadcast and Sum operations. The user implemented the support for different data types within various operations.
inference-enginecppc-librarydeep-learningtvm
intel/clDNN
Aug 2018 - Sep 2018
Compute Library for Deep Neural Networks (clDNN)
Role in this project:ML Engineer
ML EngineerContributions:5 commits, 2 PRs, 3 comments in 1 month
Contributions summary:Sergey significantly expanded the functionality of the clDNN library by adding several new activation functions, including SIN, ASIN, SINH, COS, ACOS, COSH, LOG, and EXP. These additions involved defining the functions in core kernel files and updating relevant headers and API definitions. Furthermore, the user implemented and tested the new operations, contributing to the library's robustness and completeness.
deep-learningintelneural-networksintel-hd-graphicsneural-network
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.