Dmitry Matveev
Principal Engineer, AI Software Architecture at Intel Corporation
Leinster, Ireland
Summary
🤩
Rockstar🎓
Top SchoolDmitry Matveev is a Principal Engineer in AI Software Architecture with 15 years of experience designing high-performance inference and backend systems at Intel. He combines a deep systems and performance engineering background with hands-on contributions to major open-source projects like OpenCV and OpenVINO, improving G-API and NPU plugin execution paths and dynamic quantization patterns. A long-time Emacs enthusiast, he blends functional and object-oriented programming approaches to deliver robust, efficient solutions for edge and client AI. Dmitry has transitioned through technical leadership and management roles across IoT and client computing, maintaining active individual contributor impact while scaling teams. Based in Leinster, Ireland, he brings a rare mix of low-level optimization expertise and architectural vision that directly improves inference throughput and memory stability on real hardware. Colleagues describe him as a pragmatic optimizer who surfaces subtle performance wins through disciplined analysis and targeted refactoring.
15 years of coding experience
15 years of employment as a software developer
Bachelor's degree Economics, Bachelor's degree Economics at Higher School of EconomicsMS Computer Science, MS Computer Science at Nizhniy Novgorod State Technical University named after R.Y. Alekseev (NSTU)
English, Russian
Stackoverflow
41reputation
2kreached
2answers
0questions
Github Skills (19)
code-optimization10
c-language10
image-processing10
n10
openvino10
performance-optimization10
ai10
np10
computer-vision10
cprogramming-language10
runtimes9
run-time9
sys9
cplus9
deep-learning9
Programming languages (6)
Github contributions (5)
opencv/opencv
Sep 2018 - Oct 2022
Open Source Computer Vision Library
Role in this project:
Back-end Developer
Back-end DeveloperContributions:865 reviews, 44 commits, 51 PRs in 4 years 1 month
Contributions summary:Dmitry primarily contributes to the G-API (G-API: Fixed static analysis issue in own::Mat, G-API: Introduce LPI support for Resize). These commits focus on improving the performance and functionality of the library, specifically in the area of computer vision operations. The user has been involved in fixing issues and introducing optimizations in the G-API component. The contributions also include the integration of new features and the refactoring of existing code.
pythonvisiondeep-learningc-plus-pluscomputer-vision
openvinotoolkit/openvino
Jul 2020 - Apr 2025
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Role in this project:Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:341 reviews, 127 PRs, 660 comments in 4 years 9 months
Contributions summary:Dmitry's commits primarily focus on optimizing and extending the NPU (Neural Processing Unit) plugin within the OpenVINO toolkit. Their work involves adding new execution paths, particularly for the "W" extension, which includes modifications to compiled models and partitioning logic. The user is also involved in introducing and refining dynamic quantization (DQ) patterns, including adjustments for head/tail optimizations and addressing stability and memory management issues. The user's contributions directly impact inference performance and efficiency on Intel's hardware.
inference-enginepytorchmodel-optimizerdeep-learninggpu
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.