Building Real-World AI: From Cloud Infrastructure to Agent Simulations

Talk: Building Real-World AI: From Cloud Infrastructure to Agent Simulations

Description
As AI systems move from prototypes to production, the real engineering work begins. How do you build resilient, scalable infrastructure for planet-scale data and critical missions? And how do you reliably test the complex, autonomous agents running on top of it?
This event brings together two talks focused on the practical engineering required to build and trust real-world AI systems—from the cloud-native foundations to the advanced testing methodologies that ensure your agents are ready for production.

We’ll cover:

• The infrastructure challenges of AI-driven environmental protection
• Using Kubernetes and cloud-native tech for robust data pipelines
• The role of GPU acceleration and scalable storage for large datasets
• Why traditional tests fall short for complex AI agents
• How agent simulations can uncover failures in dynamic scenarios
• Strategies to build confidence in AI agent development and deployment

Speaker 1:
Rogério Chaves (Co-founder & CTO, LangWatch)
Rogério is the co-founder and CTO of LangWatch, a leading platform for LLM observability and AI agent testing. With over 15 years of experience in software engineering and machine learning, including his time at Booking.com, he experienced firsthand the challenges of not knowing what comes out of your models in production. That pain became the motivation for founding LangWatch: to help teams ship GenAI features confidently.

Talk: Beyond unit tests: How Agent Simulations are redefining AI Agent testing
AI agents are growing more complex, reasoning, using tools, and acting autonomously. Traditional tests and evals fall short. Rogerio (CTO, LangWatch) shows how agent simulations uncover failures, test behavior in dynamic scenarios, and bring confidence to agent development and deployment.

Speaker 2:
Andrea Gardini (Technical Consultant & CNCF Ambassador)
Andrea is a technical consultant passionate about infrastructure, cloud, and automation. Throughout his career, he has worked in different roles, from an individual contributor building infrastructure as code to an engineering manager. He is deeply involved with the community as a CNCF Ambassador, KubeTrain organizer, and public speaker.

Talk: Kubernetes and AI to Protect Our Forests: A Cloud Native Infrastructure for Wildfire Prevention
As wildfires become increasingly devastating due to climate change, leveraging technology for environmental protection is crucial. This talk focuses on the infrastructure needed to support AI-driven wildfire prevention systems using Kubernetes and cloud-native technologies. We will discuss the challenges of managing robust data pipelines for processing satellite imagery and environmental data, emphasizing the importance of GPU acceleration for AI. Additionally, we will explore strategies for efficient storage solutions to handle large datasets, ensuring scalability and performance. Attendees will gain insights into the architectural considerations and operational challenges of deploying an effective, resilient wildfire monitoring and prevention infrastructure.

Agenda:
18:00 — Arrival, pizza & beer
18:30 — Talk #1 | Rogério Chaves
19:15 — Short break
19:30 — Talk #2 | Andrea Gardini
20:15 — Open conversation, networking & more drinks
21:00 — Wrapping up

What to bring:
Just curiosity and questions. If you're working on AI infrastructure, agent testing, MLOps, or resilient platform design, we’d love to hear your thoughts.

Who this is for:
Platform engineers, AI/ML engineers, SREs, architects, and engineering leaders focused on building and validating reliable AI systems in production.

Where to find us:
Fred. Roeskestraat 100, 1076 EE Amsterdam.
Please note: For parking, the P+R at the Olympic Stadium is close by.