Andrei Gorbachev
Dublin, Ireland
Summary
🤩
Rockstar🎓
Top SchoolAndrei Gorbachev is an experienced ML engineer and performance-focused software developer with five years of industry experience and a strong academic background in mathematical modeling from Novosibirsk State University. He specializes in low-level optimization for CPUs and GPUs (C/C++, CUDA, OpenCL), with deep practical knowledge of Intel, NVIDIA and ATI architectures and SIMD/NUMA-aware techniques. His work spans implementing neural networks (including a LeNet with 0.86% MNIST error) and contributing performance-critical GPU ops to the widely used OpenVINO toolkit, where he added and optimized Gather operations for GPU inference. Andrei has a solid grounding in numerical methods (finite-volume/difference/element) and parallel algorithms, demonstrated by a parallel Maxwell solver for Xeon Phi and Fermi GPUs. Unusually for an ML engineer, he also brings hands-on 3D graphics and microcontroller experience plus prior team leadership in 3D production, which helps bridge algorithmic research and production deployment.
5 years of coding experience
13 years of employment as a software developer
Master’s Degree, Chair of Mathematical Modeling, 4.25, Master’s Degree, Chair of Mathematical Modeling, 4.25 at Novosibirsk State University, Mechanics and Mathematics Department.
Github Skills (8)
gpu-programming10
c-language10
deep-learning10
inference10
cprogramming-language10
ai10
openvino10
computer-vision9
Programming languages (1)
Github contributions (2)
openvinotoolkit/openvino
May 2021 - Dec 2022
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:12 reviews, 5 commits, 67 PRs in 1 year 7 months
Contributions summary:Andrei contributed to the OpenVINO™ toolkit by implementing and testing new functionalities related to deep learning inference. Their work involved adding and testing the "Gather-7" and "Gather8" operations within the IE CLDNN (Intel's Deep Neural Network Library) framework, specifically for GPU execution. The user's contributions involved modifying and testing existing C++ code, focusing on optimizing and deploying AI inference tasks, and they were focused on the performance aspect of the library. The code modifications also include fixing reducing operations to support Deep learning inference.
inference-enginepytorchmodel-optimizerdeep-learninggpu
andrei-cv/openvino
Apr 2021 - Aug 2024
Contributions:651 pushes, 67 branches in 3 years 5 months
pytorchdeep-learninggpuopenvino-toolkitcomputer-vision
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.