🦉
AI Engineering Handbook
About
  • Hey
  • Tech Stack
  • ML to AI Shift
  • Agentic Systems
  • Anti Patterns
  • AI Engineer
  • Roles Reimagined
  • Dream Team
  • System
    • Architecture
    • Start Simple
    • Enhance Context
    • Implement Guardrails
    • Add Routing and Gateway
    • Optimise with Caching
    • Enable Agent Patterns
Powered by GitBook
On this page

Tech Stack

PreviousHeyNextML to AI Shift

Last updated 6 days ago

AI Engineering (AIE) builds apps using existing foundation models. No building from scratch. Big companies create these models. Foundation models got powerful. APIs made them easy to use. AIE exploded.

3️⃣ Three Layers

Three layers make the AI stack:

  1. Application Layer- Product companies turn capabilities into user value

  2. Infrastructure Layer - Infra companies make capabilities accessible and scalable

  3. Model Layer - Model companies create foundational capabilities

AI Engineering focuses on the Application layer.

Product Companies build user-facing apps. Deploy fast. Iterate based on feedback.

Infrastructure Companies provide tools for product teams. B2B focus. Built for scale and reliability.

  • Inference Providers serve models through APIs. , , , , , , .

  • Database Providers serve AI-optimised retrieval. , , , .

  • Observability Providers monitor and evaluate performance. , , , , .

Model Companies create foundation models. , , , , , , .

Together AI
Cohere
Amazon Bedrock
Hugging Face
Google Vertex AI
Replicate
Fireworks AI
Pinecone
Weaviate
Qdrant
Chroma
Galileo
Phoenix
Langfuse
Opik
LangSmith
Google
Meta
Anthropic
OpenAI
Mistral AI
xAI
Stability AI