Event details
Thursday, February 27, 2025
7:45 AM - 5:00 PM GMT
IN PERSON
GenAI Loft Berlin - Day 4: Advanced Applications of GenAI – Building and Scaling AI Solutions
AWS GenAI Loft | Berlin
Day:
Thursday, February 27, 2025
Time:
7:45 AM - 5:00 PM GMT
Type:
IN PERSON
Speakers:
Svetozar Miucin | Startup Solutions Architect, AWS, Liza Zinovyeva | Applied Scientist at AWS Generative AI Innovation Center, AWS, Inaam Syed | Startup Solutions Architect, AWS, Maurits de Groot | Startup Solutions Architect, AWS, Dmitri Laptev | Sr. Startup Solutions Architect, AWS, Diana Alvarado | Sr. Specialist SA Amazon Bedrock, AWS , Alexander Barge | Sr. Startup Solutions Architect, AWS, Valery Lavrentiev | Staff Data Engineer, OneFootball, Ivan Pleshkov | Senior Rust Engineer, Qdrant, Marc Klingen | Co-founder and CEO, Langfuse
Language:
English
Level(s):
200 - Intermediate, 300 - Advanced
Speakers
Show all
Day 4 at the AWS GenAI Loft Berlin is an intermediate to advanced exploration into scalable solutions and advanced techniques for Generative AI. Tailored for professionals looking to deepen their expertise, this day focuses on building with Amazon Bedrock, leveraging Retrieval-Augmented Generation (RAG), utilizing vector databases, and implementing other cutting-edge strategies.
Throughout the day, attendees will also enjoy a welcoming atmosphere with curated snacks, breakfast, and lunch, fostering opportunities to connect and network with their peers in a collaborative environment.
Who Should Attend?
Day 4 is designed for:
- Developers
- Product Managers
- Solution Architects
- Technical Decision Makers
- AI/ML Engineers
- Data Scientists
- Startup Founders
This day is for individuals ready to explore advanced techniques and build scalable, innovative GenAI solutions.
What to Expect
- Expert-Led Sessions: Gain in-depth insights into advanced strategies and scalable GenAI solutions from industry leaders.
- Cutting-Edge Topics: Dive into real-world applications and frameworks for scaling AI systems effectively.
- Networking Opportunities: Engage with AI pioneers, AWS experts, and the vibrant GenAI community.
____________________________________________________________________________________
Book a private office hour with our AWS team
Are you looking for tailored guidance on your organization? Our AWS Expert Team is here to help! Book a private office hour to dive deep into your specific challenges and get firsthand recommendations—whether it's a business strategy question or a technical deep dive.
📅 Reserve your session now: Book Here
Agenda
8:00 AM UTC
Build Your First Generative AI Application with Amazon Bedrock
Diana Alvarado | Sr. Specialist SA Amazon Bedrock, AWS
Learn how to build your first GenAI application using Amazon Bedrock, the easiest way to scale GenAI with foundation models. Discover tips for getting started quickly and explore architectures for use cases like customer support, text analysis, report generation, and forecasting trends.
9:00 AM UTC
From Prototype to Production in 60 Days: Overcoming GenAI Challenges with OneFootball
Valery Lavrentiev | Staff Data Engineer, OneFootball
Discover how OneFootball used Amazon Bedrock to transform their content tagging and entity resolution in just two months. Learn how they overcame production challenges, evaluated models, and optimized workflows to deliver superior results in content analysis and classification.
10:00 AM UTC
Building Applications Using AI Agents
Diana Alvarado | Sr. Specialist SA Amazon Bedrock, AWS
Explore how to build GenAI applications with multiple purpose-built agents that handle complex tasks. Learn techniques for orchestrating agents, managing context, and using Amazon Bedrock to create scalable AI solutions that perform tasks across use cases like customer support and knowledge retrieval.
12:00 PM UTC
Basic to Advanced RAG: Unlocking Your Complex or Large Data
Svetozar Miucin | Startup Solutions Architect, AWS
Learn how Retrieval-Augmented Generation (RAG) improves AI responses by connecting foundation models to specific datasets. Discover patterns for handling complex workflows, managing data ingestion, and writing custom code for seamless integration with your data sources.
1:00 PM UTC
Vector Databases for RAG Architectures: Comparing Options for Software Companies
Inaam Syed | Startup Solutions Architect, AWS
Examine the role of vector databases in RAG systems, enabling semantic search and intelligent chatbots. Compare AWS services like OpenSearch, Neptune ML, and Aurora PostgreSQL to find the best options for efficient, accurate, and scalable GenAI applications.
3:00 PM UTC
From Demo to Production: The Power of Traces in LLM Application Development with Langfuse
Marc Klingen & Maurits de Groot | Co-founder and CEO, Langfuse & Startup Solutions Architect, AWS
Traceability is vital for LLM application success. Marc, co-founder of Langfuse, explains how traces enhance observability, debugging, and evaluation in multi-step systems. Discover best practices for using trace data to integrate Retrieval-Augmented Generation (RAG) systems, monitor performance, identify bottlenecks, and ensure reliability, creating scalable and efficient AI-driven applications.
4:00 PM UTC
Scaling AI Applications with Vector Search Technology with Qdrant
Ivan Pleshkov & Dmitri Laptev | Senior Rust Engineer & Sr. Startup Solutions Architect, AWS
Learn how Qdrant, a top vector database on AWS Marketplace, accelerates vector search index building by 5-10x using GPU-powered AWS instances. This session explores key technical innovations, real-world applications, and performance benefits. Engineering teams will gain insights on leveraging AWS GPUs for faster indexing while maintaining search quality, with live demos and comparisons.