AI & Machine Learning Engineering

Artificial Intelligence is transforming software engineering. As a developer or DevOps engineer today, you need to understand how to build with AI — calling APIs, building RAG systems, deploying models, and monitoring AI in production.

How a Large Language Model Works

Each parameter is a floating point number, adjusted during training on billions of tokens to encode patterns of language, facts, and reasoning. GPT-4 has roughly 1.8 trillion parameters; Claude 3 has hundreds of billions; Llama 3.1 8B has 8 billion — more parameters generally means more capacity to encode nuance, at the cost of more compute to run.

The AI Stack for Engineers

Calling the Anthropic API

import anthropic

client = anthropic.Anthropic()  # Uses ANTHROPIC_API_KEY env var

# Simple completion
message = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Explain Docker in 3 sentences."}
    ]
)
print(message.content[0].text)

RAG vs Fine-Tuning — When to Use Each

|---|---|---|