Katarzyna Mitrus
Deep Learning Software Engineer at Intel Corporation
Warsaw, Masovian Voivodeship, Poland
Summary
🤩
Rockstar🎓
Top SchoolKatarzyna Mitrus is a Deep Learning Software Engineer with 10 years of experience building and optimizing ML inference tooling, currently driving core contributions at Intel in Warsaw. She has a strong C++ and Python background and a proven track record extending OpenVINO and nGraph with ONNX operator support, LSTM handling, and performance-minded integrations that enable production-ready model deployment. Her work spans backend systems, model importers, and low-level runtime improvements, reflecting both engineering rigor and practical ML deployment know-how. Prior roles in IoT and full-stack projects gave her hands-on experience with embedded Python, Qt UIs, and web frameworks, so she comfortably bridges edge, backend, and tooling concerns. She holds a master’s in Computer Science and is notable for contributing to widely used open-source inference ecosystems, improving operator coverage and robustness in industrial ML toolchains.
9 years of coding experience
3 years of employment as a software developer
Master's degree, Computer Science, Master's degree, Computer Science at Gdańsk University of TechnologyBachelor's degree, Informatyka, Bachelor's degree, Informatyka at Uniwersytet Kardynała Stefana Wyszyńskiego w Warszawie
Spanish, English, Polish
Github Skills (10)
c-language10
inference10
deep-learning10
onnx10
cprogramming-language10
openvino10
python9
testing9
build-system7
cmake7
Programming languages (3)
Github contributions (5)
openvinotoolkit/openvino
May 2020 - Jan 2023
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:1935 reviews, 121 commits, 316 PRs in 2 years 8 months
Contributions summary:Katarzyna appears to have made significant contributions to the OpenVINO toolkit, specifically focusing on optimizing and deploying AI inference. Contributions include code changes related to the nGraph framework, in particular, reordering LSTMSequence inputs and outputs, and adding support for ONNX operators such as Usample and DequantizeLinear, and for the introduction of the FakeConvert. These changes involved modifying C++ code to support and optimize the machine learning models and extending support to complex operations such as embedding bag. The user also integrated newly added ONNX operator like "Multinomial" as well as improved existing ones like "GatherND" to support new scenarios and cases
inference-enginepytorchmodel-optimizerdeep-learninggpu
NervanaSystems/ngraph
Nov 2019 - May 2020
nGraph - open source C++ library, compiler and runtime for Deep Learning
Role in this project:Back-end Developer
Back-end DeveloperContributions:228 commits, 22 PRs, 281 pushes in 6 months
Contributions summary:Katarzyna made significant contributions to the nGraph library, primarily focusing on the implementation and integration of ONNX operators, specifically the CumSum and Subtract operators. Their work included adding new operators to the ONNX importer, writing tests for these operators, and modifying existing code to support the new functionality. The user also refactored headers in the ONNX importer, added provenance tags, and updated the library to use nGraph ops from new opset headers. This suggests a strong focus on extending and maintaining the core functionality of the library.
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.