AI Engineering encompasses the end-to-end development and deployment of intelligent, autonomous AI systems and agents. This course teaches you how to build AI solutions using advanced language models, agent workflows, and integration with external tools.
You will begin with core concepts of agentic AI, learning to design autonomous systems featuring memory and workflow orchestration. Next, you will develop practical skills in LangChain and LangGraph to create scalable AI applications and multi-agent configurations.
The course also covers the Model Context Protocol (MCP) to securely provide context to AI agents, alongside Python programming for building and deploying AI workflows, from prototype through to production.
You will explore Retrieval-Augmented Generation (RAG) to enhance AI with real-time data, as well as multi-modal AI capabilities including image and audio processing.
Finally, you will study deployment essentials such as Docker, CI/CD pipelines, monitoring, and security, equipping you to build reliable and scalable AI applications.
Technologies and Concepts Covered
Python Foundations: Modern Python 3.10+ best practices including type hints, dataclasses, async programming, API handling, packaging, virtual environments, dependency management, and test-driven AI development.
Agentic AI and LLMs: Fundamentals of Large Language Models, definitions and design patterns of agentic AI, differences between autonomous and tool-assisted agents, and paradigms such as ReAct, Plan-and-Execute, and Tree of Thoughts.
Model Context Protocol (MCP): Open standard architecture connecting models to external tools; building Python MCP servers; managing security, permissions, and scalability; use in multi-agent systems.
LangChain Core: Key components like LLMs, Chains, Agents, Memory, and Tools; building prompt pipelines; integrating web search, document retrieval, API connectors; tool selection and execution strategies.
LangGraph Workflows: DAG-based orchestration for complex agent workflows; multi-agent collaboration patterns (Planner, Executor, Critic); state management and branching logic; integration with MCP for real-time external data.
Retrieval-Augmented Generation (RAG): Embeddings, vector databases (FAISS, Chroma, Pinecone); context injection techniques; building RAG agents with memory and live document search.
Agent Memory and Tooling: Managing short-term and long-term memory in agents; OpenAI function calling with JSON output; building and integrating custom tools into agent loops.
Deployment and LLMOps: Packaging LangChain and LangGraph apps for production; deploying using FastAPI and Docker; cloud hosting options (AWS, GCP, Azure); monitoring, logging, and tracing with LangSmith and Weights & Biases.
Testing, Evaluation and Responsible AI: Prompt regression testing; agent behaviour evaluation metrics; implementing guardrails, human-in-the-loop processes, and ethical compliance standards.
Career Accelerator Program
Premium Career-Ready Track
Note: Please note that all prices listed are exclusive of VAT. VAT will be charged separately and added to the total amount payable.
