AI Engineering Path
A builder route for learners who want to create useful AI applications, RAG systems, agent workflows, multi-agent automation, and reliable AI software.
Use this path when it matches the work you want to do
Choose this path if you want to build with Python, structure LLM applications, use frameworks carefully, and add evaluation and release checks.
Read the skip rule
Do not begin with frameworks before you understand Python basics, structured outputs, retrieval, tool boundaries, and failure modes.
Read the path outcome
A small AI application portfolio with an API backend, safe app flow, RAG design, agent workflow, framework implementation, reliability checks, and release notes.
Follow the route in this order
The order keeps prerequisites clear. If a course is already comfortable, use its detail page to confirm the syllabus before skipping it.
Python Foundations for AI
Build the Python basics needed for notebooks, data work, automation, and AI examples.
Generative AI Application Development with Python
Build small generative AI app flows with schemas, mock mode, safe tools, tests, and release checks.
FastAPI for AI Backend Development
Build typed Python API backends with routes, models, dependencies, tests, docs, and AI-ready service boundaries.
Introduction to RAG and Knowledge Assistants
Understand retrieval, source rules, citations, missing-answer behavior, and evaluation questions.
Introduction to Agentic AI and Workflow Automation
Design agentic workflows with triggers, state, tools, approvals, stop rules, and failure controls.
LangChain for LLM Applications and RAG
Build maintainable LLM workflows, RAG chains, retrievers, tools, structured output, and traces.
LangGraph for Agentic Workflows
Model agent workflows as state graphs with routes, checkpoints, human review, and recovery behavior.
CrewAI for Multi-Agent Automation
Design role-based multi-agent workflows with tasks, guardrails, logs, review points, and cost checks.
LLMOps for Reliable AI Applications
Evaluate, monitor, debug, and improve LLM apps with tests, traces, risk logs, and release gates.
Computer Vision and Multimodal AI
Understand images as data, use basic vision pipelines, evaluate outputs, and state responsible limits.
What this route includes
- Python Foundations for AI
- Generative AI Application Development with Python
- FastAPI for AI Backend Development
- Introduction to RAG and Knowledge Assistants
- Introduction to Agentic AI and Workflow Automation
- LangChain for LLM Applications and RAG
- LangGraph for Agentic Workflows
- CrewAI for Multi-Agent Automation
- LLMOps for Reliable AI Applications
- Computer Vision and Multimodal AI
Start the first course, then continue through the path
A small AI application portfolio with an API backend, safe app flow, RAG design, agent workflow, framework implementation, reliability checks, and release notes.