Decoding ML | Paul Iusztin | Substack

LLM Engineer's Handbook is finally live!

A framework for building LLM and RAG apps

Oct 22 •

Most Popular

Building a TikTok-like recommender

Nov 28 • Paul Iusztin

Retrieval-Augmented Generation (RAG) Fundamentals First

Aug 31 • Paul Iusztin

The ultimate LLM fine-tuning pipeline

Nov 16 • Paul Iusztin

ML serving 101: Core architectures

Nov 2 • Paul Iusztin

Decoding ML

Decoding ML

Join for battle-tested content on designing, coding, and deploying production-grade GenAI, LLM, recommender and MLOps systems. Every week. Every Thursday and Saturday.

Recommendations

The Neural Maze

The Neural Maze

Miguel Otero Pedrido

Real-World Machine Learning

Real-World Machine Learning

Pau Labarta Bajo

Marvelous MLOps Substack

Marvelous MLOps Substack

MarvelousMLOps

LLM Watch

Pascal Biese

Meri Nova

Meri Nova

Recent posts

Build a TikTok-like recommender from scratch!

RAG fundamentals first: Why use RAG and not fine-tune your LLMs?

Dec 7 •

Feature pipelines for TikTok-like recommenders

Feature engineering for a H&M real-time personalized recommender

Dec 5 •

The ultimate prompt monitoring pipeline

Master monitoring complex traces and evaluation while in production

Nov 30 •

Building a TikTok-like recommender

Building a recsys that scales to millions of items and users

Nov 28 •

Also on

Books

LLM Engineer's Handbook

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

Open source

LLM Twin Course

Build a production-ready LLM & RAG system

H&M Personalized Recommender Course

Build and deploy a real-time personalized recommender for H&M fashion articles.

The latest from

Build a TikTok-like recommender from scratch!

Feature pipelines for TikTok-like recommenders

generative-ai

The ultimate prompt monitoring pipeline

Master monitoring complex traces and evaluation while in production

Nov 30 •

Beyond PoCs: Building RAG systems that scale

A hands-on guide to architecting production LLM inference pipelines with AWS SageMaker

Nov 23 •

Engineer's framework for LLM & RAG evaluation

A hands-on guide to measuring what matters

Nov 21 •

The ultimate LLM fine-tuning pipeline

Master production-ready fine-tuning with AWS SageMaker, Unsloth, and MLOps best practices

Nov 16 •

Connecting the dots in data and AI systems

Simplifying MLE & MLOps with the FTI Architecture

Nov 9 •

mlops

The 6 MLOps foundational principles

The core MLOps guidelines for production ML

Sep 28 •

Experiment Tracking Essentials: Finding the Right Tool

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

Sep 7 •

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 •

Architect scalable and cost-effective LLM & RAG inference pipelines

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

Jun 6 •

CDC: Enabling Event-Driven Architectures

Transforming Data Streams: The Core of Event-Driven Architectures

Apr 11 •

recommenders

ml-system-design

ML serving 101: Core architectures

Choose the right architecture for your AI/ML app

Nov 2 •

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 •

Real-time feature pipelines for RAG

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

Aug 17 •

Building ML systems the right way using the FTI architecture

The fundamentals of the FTI architecture that will help you build modular and scalable ML systems using MLOps best practices.

Aug 10 •

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 •

Join for content on production-grade GenAI, LLM, recommender and MLOps systems