As Large Language Models (LLMs) become core to enterprise transformation, the ability to design and scale AI-powered APIs has never been more crucial. In this session, Daniel Oh, Java Champion and Senior Principal Developer Advocate at Red Hat, unpacks the intersection of LLMs, Open API standards, and cloud-native architectures, and how they collectively shape the future of intelligent, interoperable enterprise systems.

You’ll explore how OpenAPI specifications connect AI models with business applications, making integration predictable and secure. The session delves into scaling AI inference, covering GPU optimization, latency management, and distributed reliability, while showcasing how technologies like Kubernetes, Knative, and Quarkus enable operational excellence at scale.

Through real-world case studies, you will learn how enterprises are bridging AI innovation with platform engineering through API-first design, MLOps pipelines, and responsible deployment practices. The session concludes with a practical discussion on ethics, governance, and regulatory compliance, helping teams deploy AI that is scalable, efficient, and trustworthy.

What You Will Learn

• How to design AI-integrated APIs using OpenAPI and cloud-native tools

• Techniques to scale LLM inference while managing cost and latency

• How to operationalize AI through open-source technologies like Kubernetes, Knative, and Quarkus

• Patterns for aligning AI innovation with enterprise governance and ethics

Who Should Attend

Software architects, platform engineers, AI developers, and technology leaders building scalable, compliant, and intelligent API-driven ecosystems in the enterprise.