AI Engineering

0%Certificate0/87

Join the Community

What is AI Engineering?

The Three Layers of the AI Stack

The Modern AI Landscape

Python Essentials for AI

Functions, Decorators, and Generators

Object-Oriented Python and Dataclasses

Type Hints and Pydantic

Working with Files and Data

Making your first LLM API call

Understanding LLM Parameters

Structured Output from LLMs

Streaming and Conversation Management

Transformer Architecture Simplified

How LLMs Generate Text

The LLM Training Pipeline

What is Prompt Engineering?

Anatomy of an Effective Prompt

Advanced Prompting Techniques

Context Engineering

Prompt Templates and Pipelines

Defending Against Prompt Injection

Prompt Optimization and DSPy

What are Embeddings?

Choosing Embedding Models

Vector Databases

Building a Semantic Search Engine

Scaling Vector Search

Building a Production RAG Pipeline

Advanced Retrieval Techniques

RAG with Citations and Grounding

Evaluating RAG Systems

Conversational RAG

GraphRAG and Knowledge Graphs

From Text Generation to Action

Designing Tool Schemas

Multi-Tool Orchestration

Structured Workflows with Tool Use

Building MCP Clients

Remote MCP Servers

Production MCP Server Patterns

What are AI Agents?

Agent Memory Systems

Multi-Agent Systems

Agent Frameworks

Agent Reliability and Debugging

Agent Evaluation and Testing

Human-in-the-Loop Patterns

Building AI Workflows

Architecture Patterns for AI Applications

Designing for Reliability

Data Architecture for AI

Scaling AI Applications

The AI Gateway Pattern

Building AI-Powered UX

Caching Strategies for LLM Applications

Rate Limiting and API Management

Containerizing AI Applications

CI/CD for AI Applications

Monitoring and Observability

Handling Production Incidents

Iterating in Production

The AI Engineering Lifecycle

Understanding AI Application Costs

Prompt Optimization

Model Selection and Routing

Latency Optimization

Self-Hosting Models

Computer Use Agents

Deep Research Agents

Agent Protocols

Long-Running and Async Agents

Agent Sandboxing and Security

Vision Models and Image Understanding

Text-to-Image Generation

Audio and Speech Generation

Video Understanding and Generation

Building Multimodal Applications

AI Engineering

Welcome

Course Roadmap
Join the Community

Introduction to AI Engineering

What is AI Engineering?
The Three Layers of the AI Stack
The Modern AI Landscape

Python for AI

Python Essentials for AI
Functions, Decorators, and Generators
Object-Oriented Python and Dataclasses
Type Hints and Pydantic
Working with Files and Data
Async Python

Your First AI Application

Making your first LLM API call
Understanding LLM Parameters
Structured Output from LLMs
Streaming and Conversation Management

How LLMs Work

What are LLMs?
Tokenization
Transformer Architecture Simplified
How LLMs Generate Text
The LLM Training Pipeline

Prompt Engineering

What is Prompt Engineering?
Anatomy of an Effective Prompt
Advanced Prompting Techniques
Context Engineering
Prompt Templates and Pipelines
Defending Against Prompt Injection
Prompt Optimization and DSPy

Embeddings and Vector Search

What are Embeddings?
Choosing Embedding Models
Vector Databases
Building a Semantic Search Engine
Scaling Vector Search

RAG and Retrieval

What is RAG?
Building a Production RAG Pipeline
Advanced Retrieval Techniques
RAG with Citations and Grounding
Evaluating RAG Systems
Conversational RAG
GraphRAG and Knowledge Graphs
Multimodal RAG
Agentic RAG

Function Calling and Tool Use

From Text Generation to Action
Designing Tool Schemas
Multi-Tool Orchestration
Structured Workflows with Tool Use

Model Context Protocol (MCP)

What is MCP?
Building MCP Clients
Remote MCP Servers
Production MCP Server Patterns

Building AI Agents

What are AI Agents?
Agent Memory Systems
Multi-Agent Systems
Agent Frameworks
Agent Reliability and Debugging
Agent Evaluation and Testing
Human-in-the-Loop Patterns
Building AI Workflows

AI System Architecture

Architecture Patterns for AI Applications
Designing for Reliability
Data Architecture for AI
Scaling AI Applications
The AI Gateway Pattern
Building AI-Powered UX
Caching Strategies for LLM Applications
Rate Limiting and API Management

Production Deployment

Containerizing AI Applications
CI/CD for AI Applications
Monitoring and Observability
Handling Production Incidents
Iterating in Production
The AI Engineering Lifecycle

LLM Optimization

Understanding AI Application Costs
Prompt Optimization
Model Selection and Routing
Latency Optimization
Self-Hosting Models

Agentic AI

Computer Use Agents
Coding Agents
Deep Research Agents
Agent Protocols
Long-Running and Async Agents
Agent Sandboxing and Security

Multimodal and Generative AI

Vision Models and Image Understanding
Text-to-Image Generation
Audio and Speech Generation
Video Understanding and Generation
Building Multimodal Applications

Self-Hosting Models

Premium Content

Subscribe to unlock full access to this content and more premium articles.

Latency Optimization Computer Use Agents