Anna Zając
Software Engineer at Intel Technology Poland
Gdańsk, Pomeranian Voivodeship, Poland
Summary
🤩
Rockstar🎓
Top SchoolAnna Zając is a software engineer with seven years of experience building and validating low-level AI and networking systems at Intel, based in Gdańsk, Poland. She combines systems programming and automation skills—Python-driven test frameworks and Linux/Windows server configuration—with hands-on C++ backend work for deep learning compilers and inference toolkits. Her open-source contributions to Intel-backed projects like nGraph and OpenVINO show deep expertise in accelerator backends (IntelGPU, GNA), operator support, layout handling, and performance-focused refactors. She’s proven at turning complex hardware and layout issues into robust, test-covered solutions that improve import/export and runtime behavior. Comfortable across the stack from network hardware setups to LLM and RAG-related AI work, she brings both operational rigor and algorithmic sensibility. Colleagues rely on her for troubleshooting thorny interoperability problems and shipping dependable inference tooling.
7 years of coding experience
2 years of employment as a software developer
Master of Science (MSc), Teleinformation Networks and Systems, Master of Science (MSc), Teleinformation Networks and Systems at Gdansk University of Technology
Github Skills (14)
opencl10
c-language10
inference10
deep-learning10
cprogramming-language10
performance-optimization10
openvino10
implement9
testing9
algorithm9
code-optimization9
graph9
algorithms9
back-end-development8
Programming languages (5)
Github contributions (5)
openvinotoolkit/openvino
Jun 2020 - Nov 2020
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer
Back-end DeveloperContributions:19 reviews, 18 commits, 27 PRs in 5 months
Contributions summary:Anna primarily contributed to the OpenVINO™ toolkit's GNA (Gaussian Neural Accelerator) plugin. Their work focused on optimizing and improving the GNA plugin's functionality, including fixing scale factor calculations, supporting 4D eltwise operations, and supporting 3D import/output, which often involve addressing layout-related issues. The user also implemented network import functionalities from stream and added support for NHWC and NCHW layouts and the correct output blob rotation, enhancing the plugin's versatility and import capabilities. Additionally, they added new tests and corrected existing test functionalities for more comprehensive validation and regression testing.
inference-enginepytorchmodel-optimizerdeep-learninggpu
NervanaSystems/ngraph
Aug 2018 - May 2019
nGraph - open source C++ library, compiler and runtime for Deep Learning
Role in this project:Back-end Developer
Back-end DeveloperContributions:16 commits, 12 PRs, 30 pushes in 9 months
Contributions summary:Anna contributed extensively to the IntelGPU backend within the nGraph deep learning compiler. They implemented and updated operations such as Power, Sigmoid, ReluBackprop, AvgPool, And, Or, Not, Minimum, OneHot, Atan, Ceiling, Floor, Sign, Tan, MaxPoolBackprop, AvgPoolBackprop, SigmoidBackprop, Gemm, and TopK, demonstrating a focus on expanding the supported operator set. Their work involved modifying C++ code within the `intelgpu_backend.cpp` and related files to integrate these operations, enhancing the compiler's capabilities. Furthermore, they refactored and optimized code for improved performance and maintainability.
inference-enginecppc-librarydeep-learningtvm
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.