Maarten Vandeperre
Maarten Vandeperre is a Specialized Solutions Architect at Red Hat focused on platform engineering, AI enablement, and sovereign platform design. He helps organizations build modern application platforms on OpenShift that reduce cognitive load, enable developer autonomy, and keep enterprises in control of their data, technology, and AI strategy.
With a strong background in software development and clean architecture, Maarten bridges application design and infrastructure, mapping architectural principles to scalable, secure, and compliant platforms. His work spans sovereign AI, internal developer platforms, model serving, and cloud-native integration patterns. He regularly speaks at developer and AI conferences across Europe, sharing practical insights on platform engineering, AI, and digital sovereignty.
Talks
Platform Engineering 101: Building Internal Developer Platforms
Tell us what you want, what you really, really want… Developer productivity and reduced cognitive load, of course! In our world of cloud-native Java development and shift-left mentality, developers are now drowning! They have an endless flood of tasks and responsibilities on their shoulders, whilst battling an ever-increasing sea of potential technologies and tools to use. Change is needed! So, build a dam with us through platform engineering and IDPs. In this session, we’ll explore the concepts of platform engineering and Internal Developer Platforms (IDPs) and how they can help to relieve the cognitive load on developers, help to standardize technologies and tools used throughout an organization, streamline CI/CD pipelines and in essence enable greater developer productivity. We’ll investigate how this can all be achieved in the cloud, with example applications running in OpenShift, with Red Hat Developer Hub as the basis of our IDP.
Owning the inference layer: When and how to run your own models
Hosted model APIs are the fastest way to start building with Gen AI models, but they are not always the best long-term fit. As workloads grow, teams start running into harder questions around latency, cost, deployment flexibility, data boundaries, and performance tuning. This talk looks at what changes when you move from calling a hosted model API to running inference yourself. We’ll break down the practical tradeoffs between hosted and self-hosted approaches, then examine how modern open inference technologies such as vLLM and llm-d are making self-hosted AI more realistic for production systems. Rather than treating this as a debate between two camps, the session focuses on decision-making: when self-hosting is worth the added operational complexity, when hosted APIs still win, and what teams take on when they choose to own the inference layer. We'll also unpack what sovereignty is actually worth beyond the compliance checkbox: the concrete value of controlling your data boundaries, your model lifecycle, and your independence from a single provider's roadmap and pricing, and where that value is real rather than theoretical. You’ll leave with a practical framework for evaluating cost, control, performance, and architectural fit in your own environment.