Sahar Fatima
AI Framework Engineer at Intel
Canada
Summary
🤩
Rockstar🎓
Top SchoolSahar Fatima is an AI framework engineer with six years of experience building and shipping high-performance ML inference solutions at Intel, where she led engineering for the ONNX Runtime OpenVINO execution provider and managed multi-disciplinary teams delivering enterprise and edge AI deployments. She combines hands-on backend and ML engineering—contributing C# and Python integrations, build-system changes, and dynamic-shape support to prominent open-source projects like microsoft/onnxruntime—with operational leadership that scaled teams and enabled Microsoft Copilot on Windows AI OS. Her work emphasizes inference performance (memory, throughput, first-inference latency) and pragmatic deployment samples spanning quantization, cloud services, and NLP. Comfortable bridging product, sales, and distributed engineering across geographies, she also brings a hardware-aware perspective from prior roles in silicon architecture and Qualcomm’s Hexagon ecosystem. A PG Diploma in ML/AI complements deep embedded and image-processing roots, enabling her to translate research-grade models into production-ready runtime features.
5 years of coding experience
18 years of employment as a software developer
Bachelor's Degree, Electronics and Communication, Bachelor's Degree, Electronics and Communication at Motivational PathwayPG Diploma , Machine Learning and Artificial Intelligence, PG Diploma , Machine Learning and Artificial Intelligence at International Institute of Information Technology Bangalore
Github Skills (23)
python10
machine-learning10
openvino10
onnxruntime10
dotnet-core10
object-detection10
computer-vision10
csharp10
nuget9
ml9
onnx9
hardware-acceleration9
yolov49
neural-network9
mle9
Programming languages (3)
Github contributions (5)
microsoft/onnxruntime-inference-examples
Apr 2022 - Jan 2023
Examples for using ONNX Runtime for machine learning inferencing.
Role in this project:
ML Engineer
ML EngineerContributions:5 reviews, 5 commits, 10 PRs in 8 months
Contributions summary:Sahar made significant contributions to the object detection samples within the ONNX Runtime inference examples repository. Their work involved modifications to the Python code, specifically in the `tiny_yolo_v2_object_detection` sample, including preprocessing, postprocessing, and integration with the OpenVINO execution provider. They also worked on updating the `README.md` files and adapting the samples to align with PyPi packages. Additionally, the user contributed sample notebooks for the yolov4 and tiny-yoloV2 models.
deep-learningruntimeinferencemachine-learningonnx
microsoft/onnxruntime
Aug 2020 - Jan 2023
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Role in this project:Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:48 reviews, 32 commits, 46 PRs in 2 years 5 months
Contributions summary:Sahar primarily worked on integrating OpenVINO support into the ONNX Runtime, focusing on the C# API for the OpenVINO execution provider. Their contributions involved modifying build scripts, and adding support for including OpenVINO libraries in the NuGet package and enabling dynamic shapes, with a focus on features that improved deployment for specific versions. They also made changes to the core OpenVINO backend and implemented the new features for new releases, including fixing compilation issues. The user demonstrated a strong understanding of the OpenVINO integration process.
runtimetrainingtensorflowai-frameworkaccelerator
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.