Track 3 – 2024

angelo

Registration – 2024
-
angelo angelo

Keynote: Why does everyone keep talking about Generative AI?
-
Keynote
Keynote
angelo angelo

Break
-
angelo angelo

Managing EKS Clusters at Scale using Blueprints and Infrastructure as Code
-
Presenter: Julia Furst Morgado

Abstract: We get it – deploying complex and repeatable Kubernetes clusters with all your favorite configurations, add-ons and applications is difficult, time-consuming and error-prone. Luckily, Amazon EKS Blueprints make this process much easier. The blueprints allow DevOps teams to abstract away the challenges of infrastructure deployment through integrated CI/CD pipelines using simple, consistent code. Meanwhile, operations teams benefit from the simplified deployment of secure, optimized "well-architected" clusters. EKS Blueprints consolidate common Kubernetes tools and best practices like scaling, monitoring, security, and Day 2 tools such as backup and DR into a centralized platform. As a result, developers can reliably leverage Kubernetes across diverse teams and environments in their enterprise. For organizations maintaining clusters across multiple cloud accounts and geographies, using Infrastructure as Code with EKS Blueprints is key to automating standardized deployments with just a single line of configuration code.

AWS Services: Amazon EKS, AWS CloudFormation, AWS CDK

Audience: Advanced

angelo angelo

Clinically-validated, online mental health diagnosis using AI/ML
-
Presenter: Nathan Hiscock

Abstract: Explore the technology and research behind how AWS ML services like Rekognition and Transcribe were applied to give mental health patients online mental health evaluations that meets or exceeds the current gold standard of care.

AWS Services: Transcribe, Rekognition,

Audience: Business Focused

angelo angelo

How to Explain AWS to Non-Technical People S3 – Sophisticated Storage System AI Assisted Data Engineering on the AWS Platform
-
Presenter:Justin Wheeler

Abstract: Struggling to explain your exciting world of AWS to friends and family? This talk tries to eliminate the communication gap between technical audiences and their loved ones. We'll explore practical analogies to make cloud computing concepts clear and relatable; even to those without a technical background. Beyond simply understanding your day-to-day work, this talk empowers you to foster positive connections that extend past the tech industry. Dismantle the myth of tech exclusivity – anyone can grasp the power of the cloud with the right approach. This session is perfect for any AWS enthusiasts who would like to: * Communicate the value of AWS in an engaging way * Bridge the tech talk gap with loved ones * Promote a more inclusive image of the tech industry Join us and unlock the power of clear communication with the magic of AWS analogies!

AWS Services: None

Audience: Beginner

angelo angelo

Go Beyond The Hype – How To Build Value with AI/ML + GenAI
-
Presenter: Nathan Hiscock, Darko, Dave Stauffacher, Lena

Abstract: Panel discussion. Companies are now seeing it's not enough just to incorporate ai/ml - it can be expensive and impede agility if not done with best practices. What are some of the trends we're seeing as AI begins to mature on cloud platforms? What are some of the strengths and weaknesses of AWS vs other cloud platforms? How do we help customers find value with the right technical strategies?

AWS Services: Sagemaker, Transcribe, Amazon Q, Bedrock et al

Audience: Advanced

angelo angelo

Lunch
-
angelo angelo

Secure your App from bots and attacks with AWS WAF (Web Application Firewall)
-
Presenter: Lena Taupier

Abstract:

AWS Services:

Audience:

angelo angelo

Avoiding Common Pitfalls with Hosting Machine Learning Models
-
Presenter: Max De Jong

Abstract: With the explosion of interest in machine learning, model weights are available for many custom architectures trained on very specific tasks. Often, the repositories storing these models were created to demonstrate performance on a standard task-specific benchmark at the expense of practical considerations required for these models to be useful in real-world applications. Common issues include managing dependencies (particularly CUDA with deep learning models), exposing models as endpoints, orchestrating multiple microservices around different models, scaling up web servers to handle concurrent requests, and scaling down GPU instances for cost optimization. In this talk, I will address solutions to these common problems using technology supported by AWS as well as AWS-native solutions. These challenges and associated solutions will be concretely grounded by a recent project exploring 3D pose estimation in videos. I will share the trajectory of this work, from unconnected code repositories to an on-prem service and finally to a scalable service hosted on AWS. I will document both specific solutions to problems encountered and also focus on broader takeaways to hopefully help interested community members avoid common pitfalls in hosting machine learning solutions.

AWS Services: S3, EC2, Fargate, Gateway, Lambda, ECR, ECS

Audience: Beginner

angelo angelo

Intelligent Document Processing for Artificial Intelligence
-
Presenter: Cameron Williams

Abstract: Smart Search: the largest Amazon Textract consumer globally. Built to make document content searchable and to enable AI/ML opportunities, helping put benefits in the hands of our Veterans faster! Hear how we built a system that processed over 500 million documents in less than a year, and some lessons learned.

AWS Services: Textract, OpenSearch, S3, Lamda, SQS, SNS, Comprehend, Step Functions

Audience: Beginner

angelo angelo

How does RAG REALLY work?
-
Presenter: Jeff Maruschek

Abstract: "How many manuals are you expected to know cover to cover? How many different manuals are needed to be referenced for the same situation? You might be interested in RAG. Retrieval-Augmented Generation (RAG) is the process of optimizing the output of a large language model, so it references an authoritative knowledge base outside of its training data sources before generating a response. Large Language Models (LLMs) are trained on vast volumes of data and use billions of parameters to generate original output for tasks like answering questions, translating languages, and completing sentences. RAG extends the already powerful capabilities of LLMs to specific domains or an organization's internal knowledge base, all without the need to retrain the model. It is a cost-effective approach to improving LLM output so it remains relevant, accurate, and useful in various contexts. In this Session, Jeff Maruschek (AWS Sr. Solution Architect) will provide an overview of RAG, Context, Embeddings, and demonstrate both a fully built RAG chatbot application and AWS’s fully managed RAG offering, Knowledge Bases for Amazon Bedrock."

AWS Services: Bedrock, Lambda, Cloudfront, S3, and more

Audience: Beginner

angelo angelo

Generative AI in Real Life – GenAI and Manufacturing
-
Presenter: Rob Sable & Kathie Clark

Abstract: Generative AI tools have quickly captured the world’s attention. There’s a lot of potential, speculation, and hype. This increase in focus is being driven by the massive proliferation of data, the availability of on-demand compute capacity, and the advancement of machine learning technologies. Manufacturers leveraging AI technologies have already realized great benefits by transforming their business in areas like predictive maintenance, quality, and demand forecasting. Going forward, manufacturers are thinking about how AI can enable transformation across the entire business including • Personalizing the customer experience • Enabling employees to make better data-driven decisions, faster • Improving efficiency of business

AWS Services: Amazon Bedrock, Amazon Forecast, Amazon Lookout for Equipment, Amazon Monitron

Audience: Business Focused

angelo angelo

Building a Generative AI Chatbot
-
Presenter: Trevor Bennett

Abstract: "Have you ever interacted with a large language model, only to realize that its answers are generic, and possibly even made up? This is an evergreen issue in cases where answers to the questions exist, but the model lacks the ability to find them, because it was never trained on the data in question in the first place. We have the data (somewhere), and we have the model, how do we make them talk? Retrieval augmented generation is a technique wherein you take a user's question, enhance it for the purposes of a document query, and then use those same documents to contextualize the user's question to the model. We're going to build a workflow that does exactly that. In this talk we will walk through the architectural decisions and design constraints that lead to us using LangChain, Amazon Bedrock, and Open Search to build out a retrieval augmented GenAI pipeline. We will conclude with a comparative demonstration of results and a discussion of lessons learned."
AWS Services: bedrock, bedrock agents, lambda, s3, dynamodb, open search

Audience: Beginner

angelo angelo

Things AWS could learn from Azure (and things it shouldn’t) LinkedIn profile and strategies for earning the Top Voice award
-
Presenter: Andrew May.

Abstract: As a long time AWS user, I've been working on an Azure project for the last year. This has been an opportunity to compare the two platforms and see what each one does best. I’ll talk about some of the things I think AWS could learn from Azure, and some of the things I really hope it never adopts. Areas covered will include resource management, pricing, availability zones and Lambda functions.

AWS Services: Various

Audience: Advanced

angelo angelo

Happy Hour
-
angelo angelo