Abstract: 

Join us for a hands-on session designed for backend and data engineers looking to integrate AI into their workflows. In this one-hour session, you'll get a practical introduction to Large Language Models (LLMs) and learn the essentials of crafting effective prompts through prompt engineering. We'll explore how AWS Bedrock simplifies model deployment and fine-tuning for real-world applications. The session will begin with an overview of LLMs, followed by an introduction to prompt engineering and key techniques for crafting effective prompts. Afterward, we’ll dive into AWS Bedrock, showcasing its features and capabilities, and how it enables seamless model deployment and fine-tuning in backend and data engineering workflows. The session will include a live demonstration of setting up AWS Bedrock and deploying an LLM model, followed by a Q&A to address any questions. Whether you're new to LLMs or looking to enhance your AI capabilities, this session will provide valuable insights and actionable takeaways.

Agenda:
Introduction to LLM and Prompt Engineering (10-15 min)

Overview of Large Language Models (LLMs)
Basics of Prompt Engineering
Key prompt engineering techniques and best practices
AWS Bedrock Overview (25 min)

Introduction to AWS Bedrock
Features and Capabilities
Bedrock’s role in model fine-tuning, deployment, and backend/data engineering workflows
AWS Bedrock Demo (10 min)

Live demonstration: Setting up AWS Bedrock and deploying an LLM model

Bio: 

Elad is a Tech Lead at TeraSky CTO Office, a global provider of multi-cloud, cloud-native, and innovative IT solutions. With experience in principal engineering roles at Agmatix, JFrog, IDI, and Finjan Security, his focus lies in software architecture and DevOps practices. He is a strong advocate for fostering a DevOps culture, enabling organizations to enhance their software architecture and streamline cloud-native operations.