Georgii Evtushenko
Software Engineering Manager at NVIDIA
California, United States
Summary
🤩
Rockstar🎓
Top SchoolGeorgii Evtushenko is a Software Engineering Manager based in California with a decade of experience building high-performance computing and parallel-algorithms software. He progressed from researcher and solver-team lead roles to senior engineer and now manager at NVIDIA, bringing deep domain expertise in CUDA, C++ parallel primitives, and algorithm optimization. His open-source contributions to prominent NVIDIA projects like thrust, cub, and the stdexec proposal show hands-on impact—reducing merge-sort comparisons, integrating CUB merge sort, and adding CPOs for async execution. Georgii combines research-grade rigor from national labs and academia with pragmatic leadership delivering performant solver and library code at scale. He is particularly adept at finding and fixing subtle algorithmic and portability issues across architectures, a skill that quietly accelerates downstream performance for large developer ecosystems.
10 years of coding experience
8 years of employment as a software developer
Master's degree, Mechatronics, Robotics, and Automation Engineering, Master's degree, Mechatronics, Robotics, and Automation Engineering at Moscow State University of Instrument Engineering and Computer Sciences (MGUPI)
Русский, Английский
Github Skills (26)
algorithm10
asynchronous10
thrust10
algorithms10
c-language10
parallel10
gpgpu10
parallelization10
async10
gpu-programming10
data-structure10
kernel10
parallel-processing10
parallel-computing10
mergesort10
Programming languages (5)
Github contributions (5)
NVIDIA/cub
May 2021 - Jan 2023
[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl
Role in this project:
Back-end Developer & Algorithm Engineer
Back-end Developer & Algorithm EngineerContributions:271 reviews, 213 commits, 195 PRs in 1 year 8 months
Contributions summary:Georgii primarily contributed to the NVIDIA CUB library by implementing and fixing various functionalities related to block shuffle, merge sort, and radix sort operations within the CUDA environment. These contributions involved code modifications and additions within the core library code, including handling edge cases and ensuring correct operation within different block sizes and data types. The user also focused on optimizing code, removing unnecessary elements, and improving the documentation of the library.
cxxprimitivesnvidia-hpc-sdknvidiacpp20
NVIDIA/stdexec
Dec 2021 - Jan 2023
`std::execution`, the proposed C++ framework for asynchronous and parallel programming.
Role in this project:Back-end Developer
Back-end DeveloperContributions:59 reviews, 152 commits, 20 PRs in 1 year 1 month
Contributions summary:Georgii primarily contributed to the `std::execution` framework, focusing on improvements and bug fixes. Their work involved resolving name conflicts with external libraries and addressing issues in core components like `__schedule_task` and `transfer_when_all`. Additionally, they added new CPOs (Customization Point Objects) to enhance the framework.
stdcppasynchronousconcurrencyparallel
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.