Syed M. Shaaf
Shaaf is a Principal Architect at Red Hat. A contributor to Konveyor community a CNCF Sandbox project.
Mostly developing code with Java, Node and recently AI/ML. Shaaf is a technical editor at InfoQ and spends his time writing about Kubernetes, Security and Java. For the last 20 years, he has helped customers create and adopt open source solutions for applications, cloud and managed service, continuous integration environments, and frameworks.
Proposals - Montreal 2025
A Java Developer's Guide to Understanding, Tuning, and Apply
Discover how Java developers can harness Large Language Models (LLMs) in applications, exploring when to avoid LLMs, leverage them with Retrieval-Augmented Generation (RAG), or fine-tune models for specific needs. Through my personal journey, we’ll cover prompt engineering, zero-shot/few-shot learning, similarity search, and summarization, helping you decide when and why to use or fine-tune LLMs in your Java projects
Application Modernization: Static code analysis + LLMs
This talk presents an approach that utilizes static code analysis coupled with Large Language Models (LLMs) to facilitate automated code transformation. The method comes from the tool "Kai", which analyzes static code to pinpoint areas within source code requiring modification. Kai uses the power of LLMs to generate code changes to resolve identified incidents. It eliminates the need for fine-tuning LLMs. This session includes live code and demo.
