Shervin Emami is an embedded architect specializing in processor efficiency with 14 years of industry experience across Silicon Valley, Dubai, Australia, Florida and the Philippines, focused on real-time AI, computer vision and autonomous systems for automotive and robotics. He combines deep hands-on expertise in ARM CPU optimization (including multi-core NEON assembly), GPU/CUDA acceleration and NPUs with practical system-level experience in video codecs, VPU integration and embedded SOCs. At NVIDIA he helped lead and optimize VisionWorks and represented the company on the OpenVX standards committee, and his Jetson community work reflects a strong developer-ecosystem mindset. He currently drives performance and power improvements for HW-accelerated eye-tracking and ADAS at Seeing Machines, bringing product-focused optimisation to safety-critical domains. An active open-source contributor and co-author (notably to the Mastering OpenCV codebase and tutorials with millions of views), he pairs deep technical craft with occasional team leadership and technical marketing experience.
14 years of coding experience
9 years of employment as a software developer
Master of Philosophy, Robotics, Master of Philosophy, Robotics at The University of Queensland
Code for the book "Mastering OpenCV with Practical Computer Vision Projects" by Packt Publishing 2012.
Role in this project:
Full-stack Developer
Contributions:38 commits, 1 PR, 14 pushes in 4 years
Contributions summary:Shervin contributed to the "Mastering OpenCV" book's code repository, making various changes related to image processing and computer vision techniques. They implemented and refined image utility functions, particularly for the Android platform. Furthermore, the user addressed code related to face tracking and pose estimation, incorporating necessary includes and fixing errors. The user also modified code related to number plate recognition.
Contributions:9 commits, 5 pushes in 8 years 6 months
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.