Conference45min
Defense against the dark arts of AI: The playbook for a sovereign model-as-a-service platform
This session teaches engineers how to build a secure, private, open-source Model-as-a-Service platform, avoiding the risks of third-party LLM APIs. Attendees will gain practical guidance on access control, analytics, and cost management, empowering them to confidently deploy and control their own AI models.
Maarten VandeperreRed Hat
Camille NigonRed Hat
talkDetail.whenAndWhere
Friday, February 6, 14:05-14:50
Room B3
talks.roomOccupancytalks.noOccupancyInfo
That bill from the Gringotts of third-party LLMs just arrived via owl post. It's... a howler. And the Aurors from your security department are asking pointed questions about which dark wizards are seeing your company's secret spells. In the rush to use powerful magic, we've dabbled in the Dark Arts of black-box APIs, trading control for convenience and inviting Dementors of risk into our infrastructure. It's time to master our own magic.
This session is for wizards of engineering who are ready to move beyond chanting borrowed incantations. We'll learn the potions and charms needed to architect a secure, private model-as-a-service (MaaS) platform using powerful, open-source magic. This isn't Transfiguration theory—it's a practical guide to creating your own Marauder's Map for models. Using API Connectivity as our all-seeing eye, we'll cast protective enchantments (access policies), consult the Pensieve of analytics, and manage our galleon spend.
Leave this session with your own spellbook to stop being a squib (i.e., a person who was born into a wizarding family but does not possess any magical powers) and start being a Master of the AI Arts. It's time to take back control, brew your own powerful potions, and deploy your models with the confidence of Dumbledore himself.
This session is for wizards of engineering who are ready to move beyond chanting borrowed incantations. We'll learn the potions and charms needed to architect a secure, private model-as-a-service (MaaS) platform using powerful, open-source magic. This isn't Transfiguration theory—it's a practical guide to creating your own Marauder's Map for models. Using API Connectivity as our all-seeing eye, we'll cast protective enchantments (access policies), consult the Pensieve of analytics, and manage our galleon spend.
Leave this session with your own spellbook to stop being a squib (i.e., a person who was born into a wizarding family but does not possess any magical powers) and start being a Master of the AI Arts. It's time to take back control, brew your own powerful potions, and deploy your models with the confidence of Dumbledore himself.
Maarten Vandeperre
Maarten Vandeperre is an experienced software professional who recently joined Red Hat as an Appdev & AI Specialized Solutions Architect. With a strong background in software development and architecture, he brings a wealth of expertise to his role. Maarten's primary focus is on application development and AI, with a particular emphasis on leveraging Red Hat's OpenShift platform from a developer's perspective.
One of Maarten's true passions lies in advocating for "clean architecture" as a guiding principle in software development. He firmly believes in the importance of designing software systems that are modular, maintainable, and scalable. As part of his dedication to this approach, Maarten strives to map these principles to infrastructure solutions, ensuring that the underlying technology supports and enhances the overall architecture. His deep understanding of integration technologies, such as API Gateways, Keycloak, Kafka, service mesh, and Camel, enables him to create seamless connections between systems while adhering to clean architectural principles, which empower organizations to thrive in the ever-evolving digital landscape.
One of Maarten's true passions lies in advocating for "clean architecture" as a guiding principle in software development. He firmly believes in the importance of designing software systems that are modular, maintainable, and scalable. As part of his dedication to this approach, Maarten strives to map these principles to infrastructure solutions, ensuring that the underlying technology supports and enhances the overall architecture. His deep understanding of integration technologies, such as API Gateways, Keycloak, Kafka, service mesh, and Camel, enables him to create seamless connections between systems while adhering to clean architectural principles, which empower organizations to thrive in the ever-evolving digital landscape.
Camille Nigon
Camille Nigon is an AI Solutions Architect at Red Hat, where she helps bring cutting-edge, open-source AI solutions to life. With a strong background in data science and a passion for solving real-world problems, Camille loves using AI to tackle tough challenges and make a meaningful impact.
She's a big believer in the power of collaboration and open innovation, and she’s especially passionate about creating more inclusive spaces in tech. Camille is actively involved in initiatives that promote diversity and help make technology accessible to everyone.
She's a big believer in the power of collaboration and open innovation, and she’s especially passionate about creating more inclusive spaces in tech. Camille is actively involved in initiatives that promote diversity and help make technology accessible to everyone.
talkDetail.shareFeedback
talkDetail.feedbackNotYetAvailable
talkDetail.feedbackAvailableAfterStart
talkDetail.signInRequired
talkDetail.signInToFeedbackDescription
occupancy.title
occupancy.votingNotYetAvailable
occupancy.votingAvailableBeforeStart
talkDetail.signInRequired
occupancy.signInToVoteDescription
comments.speakerNotEnabledComments