Paul Iusztin – Medium

Paul Iusztin

Featured Book

LLM Engineer's Handbook: Master the art of engineering large language models from concept to production

The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices

2024

Maxime Labonne, et al.

Maxime Labonne, Paul Iusztin

Stories

Pinned

Paul Iusztin
in
Decoding ML

An End-to-End Framework for Production-Ready LLM Systems by Building Your LLM Twin

From data gathering to productionizing LLMs using LLMOps good practices.

Mar 16

An End-to-End Framework for Production-Ready LLM Systems by Building Your LLM Twin

Mar 16

Pinned

Paul Iusztin
in
Decoding ML

The LLMs kit: Build a production-ready real-time financial advisor system using streaming…

Lesson 1: LLM architecture system design using the 3-pipeline pattern

Jan 5

The LLMs kit: Build a production-ready real-time financial advisor system using streaming…

Jan 5

Pinned

Paul Iusztin
in
Towards Data Science

A Framework for Building a Production-Ready Feature Engineering Pipeline

Lesson 1: Batch Serving. Feature Stores. Feature Engineering Pipelines.

Apr 28, 2023

A Framework for Building a Production-Ready Feature Engineering Pipeline

Apr 28, 2023

Paul Iusztin
in
Decoding ML

Beyond Proof of Concept: Building RAG Systems That Scale

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

2d ago

Beyond Proof of Concept: Building RAG Systems That Scale

2d ago

Paul Iusztin
in
Decoding ML

The Engineer’s Framework for LLM & RAG Evaluation

Stop guessing if your LLM works: A hands-on guide to measuring what matters

2d ago

The Engineer’s Framework for LLM & RAG Evaluation

2d ago

Paul Iusztin
in
Decoding ML

8B Parameters, 1 GPU, No Problems: The Ultimate LLM Fine-tuning Pipeline

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

2d ago

8B Parameters, 1 GPU, No Problems: The Ultimate LLM Fine-tuning Pipeline

2d ago

Paul Iusztin
in
Decoding ML

Turning Raw Data Into Fine-Tuning Datasets

How to automatically generate instruction datasets for fine-tuning LLMs on custom data

2d ago

Turning Raw Data Into Fine-Tuning Datasets

2d ago

Paul Iusztin
in
Decoding ML

I Replaced 1000 Lines of Polling Code with 50 Lines of CDC Magic

The MongoDB + RabbitMQ stack that's revolutionizing LLM data pipelines

2d ago

I Replaced 1000 Lines of Polling Code with 50 Lines of CDC Magic

2d ago

Paul Iusztin
in
Decoding ML

Your Content is Gold: I Turned 3 Years of Blog Posts into an LLM Training

A practical guide to building custom instruction datasets for fine-tuning LLMs

2d ago

Your Content is Gold: I Turned 3 Years of Blog Posts into an LLM Training

2d ago

Paul Iusztin
in
Decoding ML

Connecting the dots in data and AI systems

Simplifying MLE & MLOps with the FTI Architecture

Oct 31

Connecting the dots in data and AI systems

Oct 31