AI Engineer

intermediate 10 hours

From consumer to builder

Build AI-powered applications from scratch. Master embeddings, RAG pipelines, tool calling, and agentic architectures.

For: Developers

What You’ll Learn

Understand tokenization and attention at implementation level
Implement semantic search using embeddings
Build RAG pipelines from scratch
Create custom tools and MCP servers
Design agentic systems with proper guardrails
Build evaluation frameworks using LLM-as-Judge

Learning Path

Level 4: AI Primitives

How the engine works under the hood: tokens, attention, embeddings, and type-safe schemas

How LLMs Work

Demystify language models by understanding tokens, prediction, attention, and context windows. No PhD required.

30 min

Vectors & Embeddings

Learn how text becomes numbers that capture meaning. Understand embeddings, vector databases, and how they power semantic search and RAG.

35 min

Type Safety for AI

Learn to constrain AI outputs with schemas. Master JSON Schema, Zod, and Pydantic to build reliable, type-safe AI applications.

40 min

Level 5: Retrieval Systems

Connect LLMs to your data with RAG pipelines and semantic search

RAG Fundamentals

Connect LLMs to your data with Retrieval-Augmented Generation. Build pipelines that answer questions using your documents.

60 min

Level 6: Agentic Systems

Build loops, tools, and autonomous systems with proper safety and evaluation

Tools & MCP

Extend LLM capabilities beyond text generation. Learn how tool calling works, build your own tools, and understand the Model Context Protocol.

35 min

Agentic Architecture

Design autonomous AI systems with loops, guardrails, and evaluation. Build agents that plan, execute, and learn.

75 min

Concepts Covered

Fundamentals

Tokens & Tokenization beginner

LLMs process text as tokens — chunks of characters that form the atomic units of input and output, directly affecting pricing and context limits.

10 min

Context Windows beginner

The context window is the maximum amount of text (in tokens) an LLM can 'see' at once, including prompts, history, injected documents, and responses.

12 min

Attention Mechanism intermediate

The core mechanism that allows language models to understand how words relate to each other by dynamically focusing on relevant parts of the input.

15 min

Embeddings & Vector Representations beginner

Embeddings convert text into numerical vectors that capture semantic meaning, enabling similarity search, clustering, and the foundation for RAG systems.

15 min

Retrieval-Augmented Generation (RAG) intermediate

RAG combines document retrieval with LLM generation, allowing AI to answer questions grounded in your specific data without fine-tuning.

20 min

Structured Outputs & JSON Schema beginner

Constrain AI responses to follow a specific format using JSON Schema, enabling reliable data extraction and type-safe integrations.

15 min

Type Systems

JSON Schema for Structured Outputs beginner

JSON Schema defines the exact structure and constraints for LLM outputs, ensuring type-safe, validated responses without post-processing guesswork.

15 min

Protocols

Tool Use & Function Calling intermediate

Tool use enables LLMs to interact with external systems by generating structured function calls that applications execute and return results for.

15 min

Model Context Protocol (MCP) intermediate

MCP is an open protocol by Anthropic that standardizes how AI applications connect to data sources and tools through a unified server architecture.

12 min

Patterns

Agentic Loops advanced

Iterative refinement pattern where AI generates output, evaluates it against criteria, and improves through multiple cycles until quality thresholds are met.

12 min

Guardrails intermediate

Safety constraints and validation mechanisms that prevent AI systems from producing harmful, incorrect, or policy-violating outputs.

10 min

AI System Monitoring intermediate

Observability practices for AI systems that track model performance, costs, latency, and output quality in production.

12 min

TDD for AI Agents intermediate

Test-Driven Development adapted for AI coding agents, using tests as anchors to prevent 'vibe coding' and ensure verifiable behavior.

15 min

Golden Dataset Curation intermediate

Building high-quality evaluation datasets that anchor AI system quality - because an eval is only as good as its test cases.

12 min

Cost Optimization for AI Systems intermediate

Strategies to reduce AI infrastructure costs by 50-90% through prompt caching, batch APIs, model tiering, and context pruning.

10 min

Hands-On Exercises

Compare Chat vs RAG vs Agent intermediate

Evaluate three different AI architectures for a real-world scenario to understand when to use each approach.

compare45 min

Implement a RAG Pipeline intermediate

Build a Retrieval-Augmented Generation system from scratch. Index documents, embed queries, retrieve relevant chunks, and generate sourced answers.

build45 min

Design a Type-Safe AI Schema beginner

Design and implement a Zod schema for structured AI outputs. Learn to constrain LLM responses for reliable data extraction.

build30 min

Build an LLM-as-Judge Evaluation Pipeline intermediate

Learn to evaluate AI outputs using model-graded evaluation (LLM-as-Judge), the pattern where a stronger model grades outputs from weaker models.

build45 min

Build an LLM Tool By Hand intermediate

Implement a tool from scratch without using a framework, to deeply understand how tool calling works under the hood.

build30 min

Build a Prompt Injection Firewall intermediate

Learn to build a security layer that detects and blocks prompt injection attacks before they reach your main LLM application.

build45 min

Build a Multi-Step Agent advanced

Implement an agent that can plan, execute, and iterate on multi-step tasks with tool use and state management.

build60 min

Build a Test-Driven AI Agent Workflow intermediate

Learn to configure Claude Code hooks and Git pre-commit hooks for automated test-driven AI development, ensuring agents produce verifiable code.

build30 min

Build a Golden Dataset from Git History intermediate

Learn to mine git commit history for evaluation test cases, creating a robust dataset that captures real-world code patterns and edge cases.

build40 min

Build a Read-Only MCP Server intermediate

Create a Model Context Protocol server that exposes safe, read-only tools to AI assistants. Learn MCP architecture and identify security vulnerabilities.

build45 min