Decoding ML | Paul Iusztin | Substack

LLM Engineer's Handbook is now thriving!

A framework for building LLM and RAG apps

Oct 22, 2024 •

Most Popular

Build your Second Brain AI assistant

Feb 6 • Paul Iusztin

From 0 to Pro AI Engineering Roadmap

May 10 • Paul Iusztin

From 0 to Pro AI Agents Roadmap

May 31 • Paul Iusztin

LLMOps for production agentic RAG

Mar 20 • Paul Iusztin and Anca Ioana Muscalagiu

Decoding ML

Decoding ML

Join for proven content on designing, coding, and deploying production-grade AI systems with software engineering and MLOps best practices to help you ship AI applications. Every week, straight to your inbox.

The latest from

Paul Iusztin

Architecting Agentic RAG Systems: Transform NPCs Into AI Agents

Anca Ioana Muscalagiu

Observability for RAG Agents

Recent posts

Architecting Agentic RAG Systems: Transform NPCs Into AI Agents

Taking Python to production on AWS. Architecting scalable and modular RAG feature pipelines.

Jun 7 •

The King of Multi-Modal RAG: ColPali

Query your rich visual PDFs under a RAG web app

Jun 5 •

From 0 to Pro AI Agents Roadmap

Theory to API Deployments and LLMOps

May 31 •

From Scratch: MLOps Fine-Tuning System

End-to-End. On GCP.

May 29 •

Trishala Thakur

Also on

Books

LLM Engineer's Handbook

Master the art of engineering Large Language Models from concept to production.

Perks

Exclusive discounts on our recommended learning resources

Books, self-paced courses, learning platforms and live courses.

Free courses

PhiloAgents Course

Learn how to build an AI-powered game simulation engine to impersonate popular philosophers.

Second Brain AI Assistant

Learn how to access the collective wisdom of your own mind

Amazon Tabular Semantic Search

Build a modern search app for e-commerce products leveraging tabular semantic search.

Join for proven content on production-grade AI, GenAI, and information retrieval systems

Generative AI

From 0 to Pro AI Agents Roadmap

Theory to API Deployments and LLMOps

May 31 •

Information Retrieval

The King of Multi-Modal RAG: ColPali

Query your rich visual PDFs under a RAG web app

Jun 5 •

Stop using text-to-SQL for search. Here's why.

Multi-attribute vectors + natural language are changing how we find products online

Jan 16 •

Using LLMs to build TikTok-like recommenders

The fifth and final lesson of the “Hands-On Real-time Personalized Recommender” open-source course — a free course that will teach you how to build and…

Jan 9 •

Deploy scalable TikTok-like recommenders

Ship to the real world an H&M recommender using KServe

Dec 26, 2024 •

Forget text-to-SQL: Use this natural query instead

Tabular semantic search engine on e-commerce using natural queries

Dec 19, 2024 •

ML System Design

Stop building AI demos that die

E2E MLOps architecture guide: Real-time fraud detection use case

Mar 22 •

Monolith vs micro: The $1M ML design decision

The weight of your ML serving architectural choice

Jan 23 •

ML serving 101: Core architectures

Choose the right architecture for your AI/ML app

Nov 2, 2024 •

Build a semantic news search engine with 0 delay

How to build a real-time news search engine using Kafka, vector DBs, RAG and streaming engines.

Sep 21, 2024 •

Real-time feature pipelines for RAG

RAG hybrid search with transformers-based sparse vectors. CDC tech stack for event-driven architectures.

Aug 17, 2024 •

MLOps

Deploying LLMs: Cloud, Metal, Serverless

DeepSeek-R1: GCP, Latitude.sh, Modal

May 15 •

and

Louis-François Bouchard

The 6 MLOps foundational principles

The core MLOps guidelines for production ML

Sep 28, 2024 •

Experiment Tracking Essentials: Finding the Right Tool

Gradio’s Custom Dashboards vs Wandb’s Built-In Tools for Training Diffusion Models

Sep 7, 2024 •

Anca Ioana Muscalagiu

The LLM-Twin Free Course on Production-Ready RAG applications.

Learn how to build a full end-to-end LLM & RAG production-ready system, follow and code along each component by yourself.

Jun 20, 2024 •

Architect scalable and cost-effective LLM & RAG inference pipelines

Design, build and deploy RAG inference pipeline using LLMOps best practices.

Jun 6, 2024 •

Join for proven content on production-grade AI, GenAI, and information retrieval systems

Newsletter

Architecting Agentic RAG Systems: Transform NPCs Into AI Agents

Taking Python to production on AWS. Architecting scalable and modular RAG feature pipelines.

Jun 7 •

Implement RAG agents with LangGraph

From 0 to an AI engineer PRO - A system. Designing the ideal fine-tuning dataset generation pipeline.

May 24 •

Worth it? My AI book journey

From blank page to Bestseller

May 18 •

The tech stack for production AI agents

Architecting data pipelines for AI systems. AI builders bootcamp.

May 17 •

Offline vs. online ML pipelines

Architecting a dataset generation feature pipeline

May 3 •

Guests

The King of Multi-Modal RAG: ColPali

Query your rich visual PDFs under a RAG web app

Jun 5 •

From Scratch: MLOps Fine-Tuning System

End-to-End. On GCP.

May 29 •

Trishala Thakur

5 AI Projects For People in a Hurry

From beginner to advanced (with code examples)

May 22 •

Deploying LLMs: Cloud, Metal, Serverless

DeepSeek-R1: GCP, Latitude.sh, Modal

May 15 •

and

Louis-François Bouchard

How to debug ML deployments 20x faster

Test Databricks model deployments locally

Apr 26 •

Maria Vechtomova

and

Join for proven content on production-grade AI, GenAI, and information retrieval systems

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts