AI Application Engineer Course

Course Syllabus

• Python Programming & Data Processing
  • Python fundamentals, data structures, control logic, & functions
  • Libraries, error handling, & file operations
  • Pandas Series, DataFrames, data import/export, & cleaning
  • Filtering, transformation, aggregation, pivot tables, & large datasets
• Machine Learning & Model Foundations
  • Supervised learning: Regression, classification, & evaluation metrics
  • Decision Trees, KNN, SVM, & ensemble methods
  • Unsupervised learning: K-Means clustering
  • Neural networks, deep learning, & language model foundations
• Building AI Services with FastAPI
  • FastAPI, Uvicorn, Pydantic validation, & MySQL integration
  • Integrating Python & AI logic into REST API endpoints
  • File uploads, OCR, image processing, & AI service architecture
• Generative AI & Advanced Prompt Engineering
  • LLM fundamentals: Tokens, embeddings, transformers, & context
  • Zero-shot, few-shot, role-based prompting, & prompt chaining
  • Structured outputs, document summarization, & conversational state
  • Prompt patterns, libraries, injection security, & responsible AI
• Retrieval-Augmented Generation (RAG) Systems
  • Document loading, chunking strategies, & vector databases
  • Semantic search, embeddings, & ranking/reranking
  • Building RAG pipelines with LangChain & evaluating response quality
• Agentic AI, Multi-Agent & Connected AI Systems
  • AI agents: Goals, tool registries, planning, & memory loops
  • Multi-agent workflows with LangGraph: Sequential, parallel, & supervisor
  • Model Context Protocol (MCP) servers, tools, & capability discovery
  • Agent-to-Agent (A2A) communication & connected AI architecture
  • Observability, evaluation, containerization, & deployment
• Additional AI Technologies & Tooling
  • Deep Learning, Computer Vision, & Image Generation
  • Running LLMs locally & practical tooling (LangChain, LangGraph, LlamaIndex, N8N, CrewAI)