Preetha Veeramalai
Senior Software Development Engineer at Intel Corporation
Coimbatore, Tamil Nadu, India
Summary
👤
Senior🎓
Top SchoolPreetha Veeramalai is a Senior Software Development Engineer with 4 years of experience specializing in deep learning model engineering and deployment. Based in Coimbatore, she has practical expertise in TensorFlow and Python, and has a proven track record porting and validating DL pipelines for specialized hardware at MulticoreWare and now contributing to performance-focused ML infra at Intel. Her open-source work includes meaningful contributions to the high-profile ONNX Runtime project—improving the OpenVINO execution provider and core runtime stability—demonstrating a focus on integrating accelerators for real-world inferencing. A strong computer science graduate (9.2 GPA) who pairs hands-on coding with clear documentation and cross-team communication, she brings both implementation depth and a systems-oriented view of ML productionization.
4 years of coding experience
3 years of employment as a software developer
Bachelor of Engineering - BE, Computer Science, 9.2, Bachelor of Engineering - BE, Computer Science, 9.2 at Sri Krishna college of technology
Github Skills (14)
machine-learning10
c-language10
cprogramming-language10
onnx10
hardware-acceleration10
openvino10
python9
artificial-neural-networks9
deeplearning-ai9
neural-network9
ai-framework9
deep-learning9
pytorch8
tensorflow8
Programming languages (2)
Github contributions (5)
microsoft/onnxruntime
Jun 2022 - Jul 2022
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:16 reviews, 5 commits, 20 PRs in 20 days
Contributions summary:Preetha primarily contributed to the OpenVINO Execution Provider (OVEP) within the ONNX Runtime project. Their work involved fixing versioning issues and updating documentation related to the OpenVINO execution provider. The user also made significant contributions to the core codebase, including adding checks for session options, fixing fallback exceptions, enabling sorting of initializers for OpenVINO, and integrating with newer versions of OpenVINO. This suggests a focus on improving the integration and functionality of ONNX Runtime with OpenVINO for accelerating machine learning workloads.
runtimetrainingtensorflowai-frameworkaccelerator
intel/onnxruntime
Feb 2022 - Jan 2023
ONNX Runtime: cross-platform, high performance scoring engine for ML models
Contributions:1 release, 62 reviews, 79 commits in 11 months
pytorchml-modelsscoringdeep-learningruntime
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.