Mackenzie is the Global Startup Evangelist at AWS. His days are spent traveling the globe to meet startups, share their stories, and connect engineering teams together. Every day there are a large number of startups launching on AWS across every imaginable industry. It’s Mackenzie’s mission to find stories of startups that are helping to improve the world and share these stories with a wide audience.
Â
Prior to joining AWS, Mackenzie was the Head of Technical Operations at Betterment, the world’s largest independent robo-advisor based in NYC which manages over $8B in assets. Mackenzie was a founding engineer and Head of Technical Operations at Oscar Health, an insurance startup also based in NYC, helping to grow the company to over 400+ employees.
THIS EVENT IS NOW A VIRTUAL EVENT
Â
Due to popular demand, the AWS Modern Compute Generative AI Day is now a virtual event. We have modified the agenda and event structure to seamlessly adapt to the virtual format, ensuring an engaging and interactive experience for all participants. There is only one start time (11:00 AM PT / 02:00 PM ET).
This event is designed specifically for you to learn how to experiment, build, and scale cutting-edge generative AI applications leveraging modern compute technologies: Kubernetes and Serverless on AWS. This will be a virtual event with a mix of lectures and demos led by AWS experts.
- Learn how AWS customers are accelerating building production-ready generative AI applications with AWS modern compute in the evolving landscape of generative AI and LLMs
- Discover emerging serverless generative AI use cases and design patterns to help build fault-tolerant, cost-effective, and operationally efficient generative AI applications.
Check out the complete agenda and line-up of speakers below.
Notice: No breakfast or lunch will be provided as this is now a virtual event. There's also only one virtual session starting at 11:00 AM PDT / 02:00 PM EDT
Â
Join us to explore the building blocks and patterns for accelerating your generative AI journey using Kubernetes, AWS Serverless Compute, and AWS Integration Services. Kubernetes offers powerful orchestration for scaling generative AI workloads across cloud and on-premises environments, while Serverless Compute enables the deployment and scaling of these applications with minimal operational overhead. We'll dive into emerging generative AI use cases, event-driven architectures, and integration workflows to help you build fault-tolerant, cost-effective, and efficient generative AI applications
Join us to learn about serverless patterns that are helping developers build Gen AI solutions quickly and effectively on AWS at scale. This session will include a live demo and give you a peek into variety of architectural pattern options for developing and utilizing Generative AI use cases such as retrieval augmented generation, summarization, content generation, and intelligent chatbots.
In this session, you'll learn how to achieve scalability and performance in ML inference by harnessing the distributed power of Ray Serve and the efficient memory management of vLLM. We'll show you how to handle complex workloads with ease, ensuring fast, cost-effective deployments that scale effortlessly across your EKS cluster, powered by Karpenter and Amazon EC2 accelerated instances. Whether optimizing for latency or throughput, discover how this powerful combination can accelerate your AI-driven applications, delivering robust, cost-effective, and responsive LLM inference at any scale.
Privacy | Site Terms |Â