Mircea-aurelian Dan
AI Software Solutions Engineer at Intel Movidius
Deva, Romania
Summary
🤩
Rockstar🎓
Top SchoolMircea-aurelian Dan is an AI Software Solutions Engineer based in Deva, Romania with three years of experience building and optimizing inference software at Intel Movidius. He focuses on backend performance engineering for OpenVINO, improving VPU/NPU reliability through functional tests, device parameter tuning, and memory deallocation fixes that reduce resource usage. Having progressed from a software developer intern to a solutions engineer, he combines hands-on low-level optimization with practical deployment know-how. Trained in computer programming at Politehnica University of Timisoara, he brings a systems-first mindset to squeezing performance from edge AI hardware.
3 years of coding experience
1 year of employment as a software developer
Engineer's degree, Programare computere / Programator, în general, Engineer's degree, Programare computere / Programator, în general at Politehnica University of Timisoara
Github Skills (15)
np10
performance-tuning10
performance-analytics10
c-language10
inference10
performance-monitoring10
performance-monitor10
cprogramming-language10
performance-analysis10
n10
openvino10
performance-measurement10
optimization10
ai9
computer-vision8
Programming languages (1)
Github contributions (3)
openvinotoolkit/openvino
Aug 2022 - Apr 2025
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:50 reviews, 28 PRs, 28 comments in 2 years 8 months
Contributions summary:Mircea-aurelian primarily focuses on optimizing and improving the performance of the OpenVINO toolkit, especially related to the VPU device. Their work includes renaming and configuring device-specific parameters, such as duration. The user contributed to the creation of functional tests for the NPU plugin, which supports the performance testing of the VPU, improving the reliability and maintainability of the tool. They also addressed memory deallocation issues within the compiled model, which optimized resource usage.
inference-enginepytorchmodel-optimizerdeep-learninggpu
MirceaDan99/openvino
Aug 2022 - Aug 2022
OpenVINO™ Toolkit repository
Contributions:3 pushes in 3 days
pytorchdeep-learninggpuopenvino-toolkitcomputer-vision
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.