Summary
Saeid Masoomi is an MLops and computer vision engineer with eight years of professional experience and a decade-long hands-on background in C++, GPU programming, and AI systems design. He has built and optimized large-scale, high-throughput solutions—ranging from national fingerprint and multi-stream face-recognition engines to real-time vehicle counting and OCR pipelines—often squeezing dramatic performance gains from CUDA, TensorRT and embedded GPUs. Comfortable across the stack, Saeid blends low-level optimization (HIP/CUDA/OpenCL) with production deployment tools like Triton, TorchScript and ClearML, and crafts responsive UIs using Qt/QML for real-time monitoring. His work emphasizes privacy-aware architectures, energy-efficient inference on Jetson/Xavier devices, and scalable stream processing that supports dozens of cameras per node. Notably, he engineered a fingerprint search engine that scaled to tens of millions of matches per second and repeatedly boosted accuracy and throughput in production-grade biometrics and traffic systems. Outside engineering he studies wellness and travel, reflecting a practical curiosity that drives both technical creativity and user-centered design.
8 years of coding experience
11 years of employment as a software developer
Bachelor of Electrical Engineering, Machine Vision, Bachelor of Electrical Engineering, Machine Vision at Bu-Ali Sina University
English