Aleksandr Anenkov
Software Engineer at YADRO
Nizhny Novgorod, Nizhny Novgorod Oblast, Russia
Summary
🤩
Rockstar🎓
Top SchoolAleksandr Anenkov is a software engineer with six years of experience specializing in high-performance and distributed computing, currently working on hardware/software co-design and tracing tools at YADRO. He spent several years at Intel developing and optimizing collective communication libraries (oneCCL, Intel MPI) and contributes performance and stability fixes to high-profile open-source projects like OpenVINO, particularly improving VPU/MYRIAD backend testing and memory management. His skill set spans low-level C/C++ implementation for GPU/CPU collective algorithms, cluster administration, and performance engineering, complemented by hobbyist web development in HTML, CSS, JS and TS. A PhD candidate in computer science, he combines research-minded rigor with production-focused optimization, often reducing test runtimes and uncovering subtle memory issues that improve real-world inference deployments. Based in Nizhny Novgorod, he brings practical HPC operations experience alongside contributions to widely used AI tooling.
5 years of coding experience
5 years of employment as a software developer
PhD student, Computer Science, PhD student, Computer Science at Сибирский Государственный Университет Телекоммуникаций и Информатики
Русский, Английский
Github Skills (10)
c-language10
cprogramming-language10
performance-optimization10
testing10
openvino9
computer-vision7
inference6
deeplearning-ai6
deep-learning6
ai5
Programming languages (2)
Github contributions (5)
openvinotoolkit/openvino
Jun 2020 - Mar 2022
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:93 reviews, 34 commits, 52 PRs in 1 year 9 months
Contributions summary:Aleksandr primarily contributed to the OpenVINO toolkit by modifying and creating tests for the VPU (Visual Processing Unit) backend. Their work involved rewriting tests with deprecated APIs, reducing test execution time, and fixing issues related to VPU split operations. The user also added runtime precision information to the MYRIAD plugin, updated conditions for HW tiling, and addressed memory leaks and memory management issues within the MYRIAD plugin's API. These contributions suggest a focus on improving the performance, stability, and testing of the VPU backend.
inference-enginepytorchmodel-optimizerdeep-learninggpu
KorA6/openvino
Jun 2020 - Apr 2022
OpenVINO™ Toolkit - Deep Learning Deployment Toolkit repository
Contributions:6 PRs, 449 pushes, 53 branches in 1 year 10 months
pytorchdeep-learningdeploymentopenvino-toolkitinference
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.