AI Engineer

The complete path from your first line of Python to building production AI systems: machine learning, deep learning, LLMs, RAG, AI agents, LangGraph, MCP, fine-tuning and deployment. It has 320+ hours in Arabic and 35+ real projects.

About this track:

Companies everywhere are racing to build products on large language models. The people who can make those products work reliably in production are AI engineers. They know how models work underneath, can build with the latest LLM tools, and can ship real AI systems that are tested, monitored and deployed.

This track builds all of that, in four stages.

Stage 1: Python for Data Engineering & Data Science
You start Python from zero. You learn NumPy, Pandas, data cleaning, visualization, statistics, databases and APIs, and automation. The stage ends with an end-to-end capstone for your GitHub portfolio.

Stage 2: Machine Learning Scientist
You learn regression, classification, model evaluation, unsupervised learning, feature engineering, NLP, time series forecasting, model interpretability and production-ready ML pipelines. You complete 12 hands-on projects and an ML capstone.

Stage 3: Deep Learning with TensorFlow & Keras
You build neural networks: CNNs for computer vision, transfer learning, RNNs, transformers and modern NLP, and generative deep learning. You also learn to deploy models to production, and you finish 4 real-world capstones. This stage gives you a deep understanding of how the models behind today’s LLMs actually work.

Stage 4: AI & LLM Engineering with Python
You build on top of LLMs. The topics include:

• Working with Claude, OpenAI, Gemini and open-source models
• Prompt engineering for production
• Tool use and function calling
• Advanced RAG: hybrid search, reranking, GraphRAG and agentic RAG
• AI agents built from scratch
• LangChain and LangGraph
• MCP (Model Context Protocol)
• Fine-tuning with LoRA and QLoRA
• Multimodal AI
• AI quality and observability
• AI APIs with FastAPI
• Deployment with Docker, CI/CD and AWS

You finish with 3 full capstone builds: a RAG-powered customer support agent, a multi-agent research system, and a document intelligence platform. A dedicated module also covers the AI career path and AI consulting.