SCHOOL OF DEVOPS & AI  ·  MLOps / LLMOps

Containers for GenAI & Agentic AI

The Open-Source Way

Gourav Shah  ·  2 Full Days  ·  Intermediate → Advanced  ·  Hands-on

One real system — built one step per module

Ship one real block per module — never tools in isolation.

Container-native, not Docker-native

Docker Desktop now costs money for large orgs — we use the open standard.

What you'll be able to do

By the end of two days — as a DevOps or app/AI developer.

Two connected use cases

A clean GenAI app and a real agentic system — connected at the tool boundary.

The intelligence progression

Each AI pattern arrives exactly when it earns its keep.

The build ladder — one step per module

Each module adds exactly one rung to the same growing system.

The one constraint that shapes every lab

Apple Silicon can't pass its GPU into a container — so we wire around it.

One contract: the OpenAI-compatible endpoint

A wall socket: swap the power station, the appliance never notices.

It all runs on a 16 GB laptop

A non-negotiable design rule — engineered lean on purpose, not by luck.

The open-source tool map — one tool per job

A tidy stack: for each job, the tool we actually use in the labs.

Write the stack — don't paste it

One growing compose.yaml, hand-authored service by service.

Program at a glance

Two days, two halves — serve & package, then reason & ship.

What to bring

All free and open source — a laptop and a bit of container fluency.

LET'S BUILD

Build it once. Run it anywhere.

Container-native, not Docker-native — the open standard is the through-line.

Start with Setup → Prerequisites, then Module 1.  ·  Gourav Shah · School of DevOps & AI