Embedded Systems Engineer | FPGA Developer | AI Integration Specialist
Bridging the gap between traditional electronics and cutting-edge AI. Specializing in high-performance embedded systems, FPGA-based architectures, and AI deployment on SoC platforms.
With over a decade of experience in the electronics industry and a Master's degree in Digital Electronic Systems, I specialize in building the bridge between traditional electronic engineering and cutting-edge artificial intelligence.
My expertise spans embedded systems, FPGA-based architectures, and custom PCB design, where I focus on delivering high-performance, reliable, and efficient solutions. Over the years, I've integrated deep learning models into hardware systems, especially on System-on-Chip (SoC) platforms, optimizing designs for real-time performance in resource-constrained environments.
My journey into AI-enhanced electronics began with my master's thesis, where I first combined deep learning with digital hardware. Since then, I've been passionate about pushing the limits of what's possible—developing smarter, faster, and more capable systems.
Developed laser Base sensor software and a lightweight embedded web panel for real-time control and configuration, optimized for deployment on embedded devices worldwide.
Designed hardware and firmware for secure access systems using MIFARE cards, with efficient data processing and robust encryption protocols.
Created custom firmware and a PC interface for real-time device communication, firmware updates, and sensor data parsing.
Implemented a 5-stage pipelined MIPS processor on a Spartan-6 FPGA with modular VHDL design.
Designed and simulated an image processing core for real-time filtering applications.
Worked on AI-accelerated FPGA projects integrating deep learning inference on SoC platforms for real-time signal and image analysis.
Designed custom PCBs for embedded devices, IoT nodes, and FPGA boards, focusing on low power consumption, high reliability, and manufacturability.
Created high-speed multilayer designs for AI processing modules and advanced sensor interfaces.
Built a deep learning pipeline for detecting and segmenting tumor regions (edema, core, enhancing) in brain MRI scans, optimized for deployment on SoC platforms.
Developed AI-assisted classification systems for MRI and DICOM datasets to support clinical diagnostics.
Explored hardware-accelerated neural networks using FPGA and ARM cores for embedded AI applications.
Instructor: Eng Mohammad Amin Khadem Al Hosseini
Duration: 2 Hours
Price: Free
Learn More
Instructor: Eng Mohammad Amin Khadem Al Hosseini
Duration: 8 Hours
Price: Free
Learn More
Instructor: Eng Mohammad Amin Khadem Al Hosseini
Duration: 10 Hours
Price: Coming Soon
Learn More