Evgenya Nugmanova
Software Engineer
Dubai, UAE, Russia
Summary
🤩
RockstarEvgenya Nugmanova is a software engineer with six years of experience specializing in backend development for AI frameworks and model optimization. Based in Dubai and active in major open-source projects like nGraph and OpenVINO, she has implemented core deep-learning features such as rank propagation, dynamic shape inference, and constant folding, and improved TensorFlow model conversion and quantized operator handling. Her contributions demonstrate a strong grasp of low-level C++ systems and compiler/runtime concerns for inference workloads, along with practical experience fixing tricky iteration and reshape edge cases. Beyond typical backend work, she’s proven adept at improving model optimizer pipelines—an often underappreciated area that directly impacts model portability and production readiness.
6 years of coding experience
Github Skills (16)
tensorrt10
algorithm10
data-structures10
algorithms10
c-language10
tensor10
inference10
deep-learning10
tensorflow10
cprogramming-language10
shapes10
python10
operation10
openvino10
data-structure10
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:
Backend Developer
Backend DeveloperContributions:1318 reviews, 149 commits, 677 PRs in 2 years 8 months
Contributions summary:Evgenya's commits focus on enhancements and bug fixes within the Model Optimizer (MO) tool, specifically targeting the TensorFlow (TF) backend. Their contributions involve modifying the implementation of operators such as FakeQuantize and GroupConvolution, as well as handling dynamic shape propagation. The user demonstrated expertise in improving the conversion process and addressing specific issues related to quantized models, demonstrating a proficiency in deep learning model optimization techniques.
inference-enginepytorchmodel-optimizerdeep-learninggpu
NervanaSystems/ngraph
Sep 2019 - May 2020
nGraph - open source C++ library, compiler and runtime for Deep Learning
Role in this project:Back-end Developer
Back-end DeveloperContributions:132 commits, 34 PRs, 118 pushes in 8 months
Contributions summary:Evgenya contributed to the development and maintenance of the nGraph library, focusing on core functionalities related to deep learning. They implemented rank propagation for MatMul and Reduces operations. Additional contributions include renaming a zero_flag in the Reshape, fixing TensorIterator iterations, and implementing constant folding for v1 Subtract operations. Further contributions include improving dynamic shape inference for several operations such as Clamp, Squeeze/Unsqueeze, ConvBackPropData, NonMaxSuppression, Broadcast, and VariadicSplit.
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.