Gathering at Google Berlin: MLOps Community x GDG Cloud Berlin

Name: Gathering at Google Berlin: MLOps Community x GDG Cloud Berlin
Start: 2026-01-21T18:00:00+01:00
End: 2026-01-21T21:30:00+01:00

Google Berlin, Tucholskystraße 2, Berlin, 10117

GDG Cloud Berlin

Level up your cloud skills at the next GDG Cloud Berlin Gathering! RSVP now to secure your spot!

Jan 21, 5:00 – 8:30 PM (UTC)

206 RSVP'd

Key Themes

Community BuildingGoogle Cloud

About this event

Join the MLOps Community x GDG Cloud Berlin gathering at Google Berlin for networking and talks!
🔖 We’re all about keeping things friendly and welcoming. Please take a moment to check out our Code of Conduct to help us make this event great for everyone.
👀 Have any ideas for future events or questions about sponsorships? Feel free to reach out! We really appreciate your feedback and are eager to build a strong and fun community together.

When

Wednesday, January 21, 2026
5:00 PM – 8:30 PM (UTC)

Where

Google Berlin
Tucholskystraße 2
Berlin 10117

Agenda

▶️ 🥗 Arrival, Food & Networking
📜 Opening Remarks	Facilitated by the GDG Cloud Berlin crew: Yevgen Batovskyi, Hany Elfouly, Esra Kadah, Mohamed Islem Ayari and MLOps Community Berlin: Stefan Ojanen and Valdimar Eggertsson
⏯️ Patrick Löber — Building Agentic Applications with Gemini 3	With the release of Gemini 3, we have entered a new era of agentic AI capable of complex reasoning. This talk explores the complete stack for building these advanced agents using Google’s latest tools. We will dive into the new Interactions API which powers long-running workflows and the Live API for building voice agents. I will also cover strategies for reducing hallucination using the File Search tool for RAG and specialized tools like Google Maps. Finally, we will review how to orchestrate these pieces using open-source libraries.
⏸️ Stretch and refresh	Stretch and refresh
⏯️ Steffen Hoellinger — Pattern Recognition and Anomaly Detection for event-driven AI Agents with Apache Flink and Kafka	Specialized, event-driven AI Agents, in contrast to planning agents, provide unique value for continuously monitoring real-time event pipelines, business processes or technical logs in Apache Kafka. High-volume event pipelines can be filtered very efficiently with Complex Event Processing (CEP) as a core library in Apache Flink for pattern recognition of sequences of events, as well as traditional ML models with statistical approaches to detect anomalies for critical errors and business opportunities. AI agents can then invoke LLMs in a second step, to classify or further analyze the detected patterns or anomalies, suggesting or triggering actions. Due to these specialized tasks, small models often perform great in this context to achieve deterministic outcomes. Specifically in a business process context, this architecture provides opportunities for real-time process mining for ERP, manufacturing, supply chain and financial data to detect process issues and SLA violations earlier, reducing down time and saving costs by taking action immediately.
🎤 Open Mic Session & Networking	Facilitated by MLOps Community: Stefan Ojanen and Valdimar Eggertsson, with support from the GDG Cloud Berlin crew
⏹️ Doors close

Speakers

Patrick Löber

Google DeepMind

Developer Relations Engineer

Steffen Hoellinger

Confluent

Field CTO

Host

Katya Vinnichenko

Google

Program Manager

Organizers

Yevgen Batovskyi

GDG Cloud Berlin

Organizer

See bio

Esra Kadah

Antigua Mobile

Organizer

See bio

Hany Elfouly

Seer Real

Co-founder & CEO

See bio

Mohamed Islem Ayari

CLOUDPILOTS Software and Consulting GmbH

Organizer

See bio

Gathering at Google Berlin: MLOps Community x GDG Cloud Berlin

Jan 21, 5:00 – 8:30 PM (UTC)

Key Themes

About this event

When

Where

Agenda

Speakers

Patrick Löber

Steffen Hoellinger

Host

Katya Vinnichenko

Partner

Google

Organizers

Yevgen Batovskyi

Esra Kadah

Hany Elfouly

Mohamed Islem Ayari

Jan 21, 5:00 – 8:30 PM (UTC)