Stop by for a demo, collect limited-edition branded merch, and hear how Fireworks can provide the platform to build your Generative AI capabilities - optimized and at scale.

Tuesday, December 2, 12:00 - 1:00 pm PST
Shaunak Godbole, Field CTO, Fireworks

Join industry leaders as they share their experiences scaling AI initiatives using AWS AI infrastructures. AWS customers will present their journeys demonstrating how they optimized their AI workloads across training and inference for maximum performance and cost efficiency. Discover real-world architectures, implementation strategies, and lessons learned from organizations deploying large language models, reasoning systems, and multimodal applications at scale. Learn practical approaches to selecting and leveraging the right AI infrastructure for your AI workloads while managing costs effectively.

Roberto Barroso, Applied AI, Fireworks AI

Companies like Notion, GitLab, and DoorDash run their AI inference on Fireworks because they want to own their models without sacrificing performance. We'll show you how our stack optimizations—custom CUDA kernels, speculative decoding, disaggregated serving—enable blazing fast inference at scale. Then we'll walk through real AWS deployment patterns: fully managed multi-region or in-VPC deployment on SageMaker/EKS/ECS, or locked down in your VPC. Plus, see how to build production agents using Fireworks with AWS AgentCore.

Run and tune your open-source AI models on our highly scalable, optimized virtual cloud infrastructure. We have product experts, engineers, and executives on-site and available for meetings and demos.

Meetings will be hosted in our meeting space in the G Expo Hall, Monday, December 1 - Thursday, December 4.