Sponsor: IEEE
Speaker: Shivendra Srivastava

Date: 16 Apr 2025
Time: 05:30 PM PDT to 08:30 PM PDT
Cost:
Location: Online
Reservations: IEEE
Summary:
LLMs are in every part of our lives. They play a vital role in increasing productivity, improving creativity, and bridging the technology gap between different industries. Hard-to-optimize problems have today become when to optimize because the technology is readily available. In this talk, we will look at different aspects of Prompt Engineering, including templates, techniques, and patterns that you can use while interacting with models. We will also walk through advanced techniques such as RAG and show how implementing these can solve some limitations and real-world problems that we face today. LLMs are transforming industries by enhancing productivity, fostering creativity, and bridging technological gaps. As AI capabilities expand, the challenge is no longer whether problems can be optimized but how to optimize effectively. This talk explores the principles of Prompt Engineering, covering key templates, techniques, and patterns to enhance model interactions. We will dive into advanced strategies like Retrieval-Augmented Generation (RAG) and show their real-world applications in overcoming LLM limitations.

Attendees will walk away with actionable insights to harness the full potential of LLMs in their workflows.

Bio: Shivendra Srivastava has more than a decade of experience working in the field of Cloud/Distributed Computing, Machine Learning, and Artificial Intelligence. Shivendra is an experienced engineer and engineering manager who has worked across various industries such as Retail, Pharmacy, and more recently in Cloud Computing companies. He holds a Master’s degree in computer science from Georgia Institute of Technology.

Shivendra is an Engineering Manager at AWS, where he focuses on building highly available, low latency and scalable serverless solutions that power AWS Lambda, Athena, Glue and Bedrock.