Mahmoud M.

Generative AI , Computer Vision , Software Engineer and NVIDIA DLI ambassador/instructor having intensive experience in the following areas: 🖼️ Generative AI: image synthesis , chatbots.​ 🔍 Agentic Retrieval-Augmented Generation (RAG) Systems 🛠️ LangChain, LangGraph, and LangServer 🚀 NVIDIA Technologies: DeepStream, Jetson Nano, CUDA, TensorRT, NVIDIA Triton Inference Server, and NVIDIA NIM for efficient AI deployment.​ 📷 Computer Vision: OpenCV, Object detection, classification, segmentation and camera calibration techniques.​ ⚙️Streaming protocols:GStreamer, RTSP, RTMP, 💻 Programming Languages: C++, Python, and Bash ⚙️ DevOps Tools: Docker, Nginx, and ELK Stack (Elasticsearch, Logstash, Kibana) 🌐 Web Technologies: Knowledgeable in Angular, Node.js, PHP, MySQL, and MongoDB for full-stack development. ⚡ Accelerated Computing with CUDA in C++ and Python 🖥️ GUI Desktop Application Development with PyQt5 🍓 Raspberry Pi 5 with Google Coral Accelerator Integration 🧠 Machine Learning Frameworks: TensorFlow and PyTorch 📊 Vector Databases:ChromaDB, Milvus, and FAISS