Akamai Developer - Videos
Back to Channel
Demystifying Deep Learning: Illustrated Perceptron Tutorial with Akamai CTO Dr. Robert Blumofe
In this tutorial, Akamai CTO Dr. Robert Blumofe leverages a simple yet powerful device called the Perceptron to provide a practical, step-by-step demonstration of the key concepts underpinning deep...
Platform Engineering: Deploy 10 Platforms in 10 Regions in 10 Minutes
Just as with cloud-native applications, deploying and maintaining cloud native infrastructure means that you are taking advantage of the elasticity and abstractions provided by cloud services (a.k....
Serverless Functions with Zero Cold Starts: WebAssembly + Spin
Serverless doesn’t have to mean cold starts. Find the code over on GitHub at https://github.com/akamai-developers/serverless-url-shortener In this video, we build truly serverless functions with...
I Built a RAG App to Decode Airline Bureaucracy (So You Don't Have To)
In this video, Lena Hall shows you how to build a specialized RAG (Retrieval Augmented Generation) chatbot that reads complex legal documents and provides evidence-based answers. We are solving a r...
Deploy a Llama 3 AI Chatbot on Kubernetes (Full Walkthrough, Hugging Face + GPUs)
In this episode of AI at Akamai, we go beyond theory and show you how to deploy your first AI chatbot in under an hour — no PhD or cloud expertise required. This is a practical walkthrough for deve...
86% Cheaper Edge AI Inference? How We Did It (NVIDIA RTX 4000 vs. AWS GPUs)
In AI, speed and cost are often trade-offs — but they shouldn't be! Make them your competitive edge. In this episode of AI at Akamai, we walk through a real-world benchmark of Stable Diffusion XL ...
The Need for Speed: Real-World Edge AI Use Cases That Demand Low Latency
In edge AI, speed isn’t optional — it’s mission-critical. From smart cars to virtual try-ons, today’s most innovative AI applications depend on real-time inference at the edge to deliver seamless,...
AI at the Edge: Powering Today’s CX Hyper-Personalization | Fermyon Demo
See how AI-powered hyper-personalization is transforming e-commerce with real-time recommendations running at the edge. In this episode of AI at Akamai, we demo a live retail application built wit...
Build a Chatbot with Kubernetes & Akamai Cloud
Curious how to deploy your own AI chatbot with real-time inference, Kubernetes, and GPUs? Read the Docs to learn more. You don’t need to be a cloud expert to follow along. In this video, Mike Ell...
SpinKube for Cloud-native WebAssembly Workloads
In this talk, Thorsten Hans from Fermyon (an Akamai partner) introduces SpinKube, an open source project for deploying and managing WebAssembly (Wasm) workloads natively on Kubernetes clusters. Thi...
The Missing Piece in Scalable AI Inference
Sudeep Goswami discusses how Traefik Labs runs AI models on Akamai Cloud. In this talk, you'll learn why AI gateways are becoming essential for deploying and managing AI models as APIs, and how the...
Deploy Production-Ready K8s in Minutes with Akamai App Platform
Platform engineering initiatives often exceed budgets and timelines while losing sight of their original value. In this deep dive, we explore how Akamai App Platform solves Day 0, Day 1, and Day 2 ...
Skip the Complexity: Production-Ready K8s on App Platform
Enterprise Kubernetes adoption is high, but operational complexity remains a major challenge. Allen Duet, Director of Product Management for Cloud Native at Akamai, explains how App Platform elimin...
Production-Grade Kubernetes Without Complexity
From containerization beginners to advanced AI inference and WASM use cases, discover why performance matters across the entire cloud native journey. Gary Gaughan (Senior Product Manager, LKE) dive...
Akamai App Platform: Developer Experience Demo
See how developers deploy, scale, and manage apps with ease on Akamai App Platform. This demo walks through CI/CD workflows, Argo CD, Prometheus, Harbor, access controls, and one-click services: ht...
Install Akamai App Platform: Deploy Kubernetes Apps in 20 Minutes
In this step-by-step tutorial, Sander Rodenhuis shows you how to quickly deploy Kubernetes applications using Akamai App Platform. Learn how to provision a cluster, install App Platform, and start ...
From Prompt to Production: Unlocking AI Inference
AI inference demands rethinking your architecture - discover how deploying AI near your users boosts performance, reduces costs, and solves scaling challenges with low latency and high throughput. ...
Improve UX at Peak Traffic with Edge Waiting Rooms
When your site hits peak traffic, scaling alone isn’t always enough. Learn how Queue-it uses edge-based waiting rooms to control traffic flow, protect backend performance, and improve customer expe...