Name: AI & Cloud: Graph-Based Recommenders and Cost-Efficient Generative Architectures
Start: 2025-10-30T17:30:00+01:00
End: 2025-10-30T20:30:00+01:00
Location: Google Office Berlin

**Important! Registration possible ONLY here [https://gdg.community.dev/events/details/google-gdg-berlin-presents-ai-amp-cloud-graph-based-recommenders-and-cost-efficient-generative-architectures/](https://gdg.community.dev/events/details/google-gdg-berlin-presents-ai-amp-cloud-graph-based-recommenders-and-cost-efficient-generative-architectures/)**

**Every attendees must provide a real name with identification document in order to enter the building. Every Registration without Full Name will be deleted.**
​Join us for a deep dive into two exciting froantiers of AI. We’ll explore how graph-based approaches can enhance recommendation systems, and how to architect scalable, cost-efficient generative AI platforms using Cloud Run, GKE, and Vertex AI. Expect practical insights into building smarter algorithms and running them efficiently in the cloud.

**Agenda**
​**17:30 – Doors Open**
Arrive early, grab a drink, and meet the community before the talks kick off.
​**18:00 – Scaling Generative AI: Cost-Efficient Multimedia Platform Architecture with Cloud Run, GKE, and Vertex AI**
by **Nikolai Danylchyk**
This talk is a deep-dive into building a cost-optimized, multi-tenant platform for generating diverse multimedia content, including text, images, 2D/3D models, and audio. We will explore the technical challenges and solutions for balancing high throughput with low operational cost with Intelligent GPU Allocation, Decoupled Workloads and Granular Resource Sharing.
​☕️ Break – 10 min
​**18:50 – A Sommelier's Guide to Recommendation Algorithms: Classical and Graph-Based Recommender Systems**
by **Moritz Wegener**
Recommendation engines are all around us – on Netflix, Spotify, Amazon and many other platforms, they subtly shape what we watch, listen to, or buy. In fact, around 80% of what users watch on Netflix comes from recommendations, making these systems critical for user satisfaction and engagement. But building effective recommendation systems comes with challenges: massive datasets, complex user preferences, and the need for fast, accurate predictions.
​☕️ Break – 10 min
​**19:40 – TBD Talk**
Details to be announced — stay tuned!
​🕺 **Networking until 21:30** 💃
Enjoy discussions with the speakers and connect with fellow AI & cloud practitioners.
​🍕 Food, snacks, and drinks will be served.

Shrinish

Emy Jamalian

Louis Tsai

Mohamed islem ayari

Alex Mir

Google Developer Group Berlin (GDG Berlin)

Technology

Web Development

Web Technology

Software Development

New Technology

Google

App Engine

Computer Programming

Open Source

Google Developer Group

Android Development Operating Systems Technology

Cloud Computing

Programming Languages

AI & Cloud: Graph-Based Recommenders and Cost-Efficient Generative Architectures

Artificial Intelligence Machine Learning Robotics

Google Office Berlin

Share

AI & Cloud: Graph-Based Recommenders and Cost-Efficient Generative Architectures

Google Developer Group Berlin (GDG Berlin)

Details

Members are also interested in