Build AI That Scales: OpenSearch x AI

​Join Aiven and Google Cloud for a hands-on lab to learn building data infrastructure for AI applications in production, and how to run OpenSearch in production for AI and GenAI workloads.

​This interactive, instructor-led workshop is designed for developers and data engineers who want to build and run real-world data pipelines using open source tools.

​Note: Bring your laptop, we’ll be shipping code together.

​Agenda:
* 5:00pm~5:30pm: Check-in, Food, Networking
* 5:30pm~7:30pm: Tech talks and Hands-on Workshop
* 7:30pm~8:00pm: Q&A, wrap-up

​⚡️ Workshop 1 — Foundations: Build Your Own Pipeline
​Start from scratch and assemble a complete data pipeline using Aiven services.
- Provision and manage services
-Connect systems into a unified pipeline
​- Build an observability setup
- ​Query real-time data across services using SQL

​⚡️ Workshop 2 — Advanced: Real-Time Retail Streaming Pipeline
​Go deeper with a real, production-inspired use case.
- ​Design and implement a high-quality streaming pipeline
- Work with real-time retail data flows
- Apply best practices for scalability and reliability

​What you’ll learn:

• ​Deploy and scale OpenSearch for production

• ​Best practices for vector and hybrid search

• ​Build efficient real-time data pipelines

• ​Design and optimize RAG architectures

​​Why attend?

• ​Build a production-style data pipeline

• ​Learn how to connect Kafka, ClickHouse, OpenSearch, and PostgreSQL into a working, real-time architecture.

• ​Learn by doing and Apply proven patterns

• ​Provision services, stream data, and run queries yourself using both UI and CLI workflows.

• ​Walk away with practical approaches you can reuse for streaming, analytics, and observability use cases.

​Who Should Attend:
Developer and data engineer, interested in moving from prototype to production with OpenSearch.

​Venue:
Techspace Eiswerk Berlin