Host: Cedric Clyburn Guest: James Harmison Producer: Rohan Venkatram 👉 What you’ll see in this episode: 🏔️ Red Hat Summit 2026 Recap Key moments and announcements from the event The atmosphere, community, and biggest AI conversations Highlights from the Summit experience 🔹 Virtual Summit & AI Demo Showcase Exploring the virtual Summit experience A look at standout AI demos presented during the event How enterprises are approaching AI infrastructure and scalability 🔹 AI Autoscaling Explore how Red Hat AI enables autoscaling inference to dynamically handle changing demand. This demo highlights how models can scale seamlessly based on workload needs, delivering consistent performance while optimizing GPU and infrastructure usage. 🔹 AI Infrastructure & Cluster Management Exploring cluster configurations and resource management Scaling accelerated computing environments efficiently Enabling flexible infrastructure for modern AI teams 🔹 Real-World AI Operations on OpenShift Supporting scalable AI and ML workloads Operational simplicity for platform and infrastructure teams Modern approaches to GPU resource consumption 🔹 Interactive Q&A with Cedric & James 🕹️ Interactive Demo / Follow Along: https://www.redhat.com/architect/portfolio/detail/226-gpu-as-a-service-interactive-experience?intcmp=RHCTG0260000482129&utm_source=rhsummit2026&utm_medium=arcade&utm_campaign=ai&utm_content=ai_autoscale-ai_demo02 🎯 Episode Overview: Cedric Clyburn returns with another episode of Demo Deep Dive, joined by James Harmison for a special Red Hat Summit recap focused on AI innovation, infrastructure modernization, and GPU-powered workloads. A Red Hatter since 2019, James brings a background spanning IT infrastructure engineering, cybersecurity, system administration, and incident response. His experience building infrastructure-as-code environments, running Linux container tooling, and focusing on modern security practices provides a unique perspective on the evolving AI infrastructure landscape. In this episode, Cedric and James revisit the biggest themes and highlights from Red Hat Summit, including the growing momentum around enterprise AI, platform engineering, and accelerated computing. They also discuss the virtual Summit experience and the range of live AI demos showcased throughout the event. The conversation then shifts into a focused technical walkthrough of a GPU-as-a-Service (GPUaaS) workflow. James demonstrates how organizations can streamline GPU resource management by enabling users to reserve, allocate, and adjust GPU resources dynamically across cluster environments. As AI workloads continue demanding more scalable and flexible infrastructure, GPU management has become a major operational challenge for platform teams. This session explores how modern Kubernetes and OpenShift-based environments simplify GPU access while improving utilization, scalability, and operational efficiency. Whether you're exploring enterprise AI platforms, managing infrastructure for accelerated workloads, or looking to understand how GPU resources can be operationalized more effectively, this episode provides a practical look into scalable AI infrastructure workflows. 🔗 Learn more and interact: 📌 Explore OpenShift – https://www.redhat.com/en/technologies/cloud-computing/openshift 📌 Red Hat AI – https://www.redhat.com/en/topics/artificial-intelligence 📌 NVIDIA AI Infrastructure – https://www.nvidia.com/en-us/data-center/ 📌 Kubernetes – https://kubernetes.io/ 📌 Follow Cedric – https://www.cedricclyburn.com/ 📅 Livestream: Tuesday, May 19th @ 11am ET ▶️ Watch live or on-demand on @RedHat and @OpenShift #RedHat #OpenShift #AI #GPU #GPUaaS #Kubernetes #EnterpriseAI #HybridCloud #CloudComputing #AIInfrastructure #MachineLearning #PlatformEngineering #MLOps #RedHatSummit

 438      18