Welcome to the monthly in-person AI meetup in Chicago, in collaboration with AWS. Join us for deep dive tech talks on AI/ML, food/drink, networking with speakers & peers developers

Agenda (CDT):
* 4:00pm~5:00pm: Checkin, Food/drink and networking
* 5:00pm~5:10pm: Welcome/community update/Sponsor intro
* 5:10pm~7:10pm: Tech talks
* 7:10pm: Open discussion & Mixer

Tech Talk 1: Operationalize Fraud Detection using Graph Neural Network(GNN) in Production
Speaker: Puneet Rawal @AWS
Abstract:In this session you will learn about running production scale fraud detection using GNN, Amazon Neptune and SageMaker. We will be using customer identity and credit card transactions to train model, tune hyperparameters, deploy GNN model and run real-time inference to detect fraud as it is happening. Attendees will walk out with working example of full scale application using MLOps pipeline and SageMaker endpoints.

Tech Talk 2: Transforming Conversational AI with Generative AI and Large Language Models
Speaker: Swagat Kulkarni @AWS
Abstract:This session explores the transformative impact of Generative AI (GenAI) and Large Language Models (LLMs) on conversational AI applications. With the advent of GenAI models, developers and enterprises can effectively tackle complex challenges in natural language processing and understanding. The session highlights the benefits of LLMs, such as creating compelling conversational experiences for customer service and enhancing employee productivity. The session introduces the Retrieval Augmented Generation (RAG) technique, which retrieves relevant information from enterprise knowledge bases and combines it with user requests to improve response accuracy. Attendees will gain insights into optimizing LLM usage, addressing prompt length limitations, and leveraging GenAI for more intelligent conversational interactions.

Tech Talk 3: Fine-tune large language models using SageMaker distributed training libraries
Speaker: Kanwaljit Khurm @AWS
Abstract:Learn how to fine-tune large language models on Amazon SageMaker to build your generative AI applications. We will explore popular generative AI use cases and mechanism to fine-tune large language models using SageMaker distributed data parallel and model parallel libraries.

Venue:
Amazon Web Services Inc.
227 W Monroe St #1400, Chicago, IL 60606 Google Map
How to find us: 14th floor. Government-issued ID is required for checkin.

Community on Slack
- Event chat: chat and connect with speakers and attendees
- Sharing blogs, events, job openings, projects collaborations
Join Slack (search and join #chicago channel)