AWS User Group Cologne #AWSUGCGN

Hey everyone, join us for our forth AWS User Group Cologne in 2025 and also join our LinkedIn AWS User Group !

The meetup will be held on Thursday, October 30th, 2025, at 6:00 pm / 18:00 CET and is presented by Cologne Intelligence and hosted by Trusted Shop.

Get ready for an exciting talk by Alex Günsche (Senior Solutions Architect @ AWS) & Vivienne Amm (Associate Solutions Architect @ AWS) and a 2. talk by Vadym Kazulkin (AWS Serverless Hero and Head of Development at ip.labs) and of course a friendly get-together!

This meetup will not be hybrid so you can only participate on site.
Please register beforehand as there is only a limited room capacity.

The meetup will be held at:

Trusted Shops SE
Colonius Carré
Subbelrather Straße 15c
50823 Köln, Deutschland

Trusted Shops: https://business.trustedshops.de/

This is the agenda:
18:00 – Get together
18:15 – Intro and administrative details by Cologne Intelligence
18:30 – MLOps for Cloud Engineers: Building Production-Ready ML Pipelines by Alex & Vivienne
19:15 – Q&A
19:30 - Agentic AI meets Serverless on AWS by Vadym
20:15 – Q&A
20:30 - Socializing with Drinks & Snacks

Speaker & Talk Information:

MLOps for Cloud Engineers: Building Production-Ready ML Pipelines

• We all know the challenge of moving workloads from local development to cloud production environments. Whether it's managing environment consistency, automating deployments, or setting up monitoring and alerting, these operational concerns are familiar across all types of applications. Machine learning models present similar challenges but with additional complexity around model versioning, performance monitoring, and handling data drift over time.

In this talk, we'll explore how to apply familiar DevOps practices to machine learning workflows using AWS services. We'll examine approaches for automating ML pipelines, implementing production deployment strategies, and monitoring model performance in real-world scenarios. Topics will include CI/CD practices adapted for ML workflows, testing and validation strategies, and leveraging SageMaker tools for production ML operations. The session will include a practical demonstration of deploying machine learning models from development to production.

This talk targets developers, DevOps engineers, and cloud engineers who work with or support ML systems in their organizations. No prior machine learning expertise is required—we'll focus on the infrastructure and operational aspects that are familiar to application developers. Attendees will leave with practical knowledge of MLOps implementation patterns and AWS tooling for production ML workflows.

Meet Alex:

• Alex is a Senior Solutions Architect at AWS with 20 years of IT experience in expert and leadership roles. He is a strong advocate of agile and DevOps practices, and he enjoys seeing serverless, cloud-native and event-driven architectures deployed at scale. He has delivered large transformation projects and successfully developed own and customers’ businesses. As an international speaker, he has held advanced technology sessions at a wide range of events.

LinkedIn: https://www.linkedin.com/in/alexander-guensche/

Meet Vivienne:
Vivienne is an Associate Solutions Architect at Amazon Web Services (AWS) based in London. She works with organizations to support their adoption of AI and cloud technologies, drawing on her academic background in the field. Her master’s thesis focused on artificial intelligence and machine learning, which she used to predict the differentiation of pluripotent stem cells. At AWS, she is leading workshops and training sessions to help teams deepen their understanding of AI/ML applications and best practices.

LinkedIn: https://www.linkedin.com/in/vivienne-amm/

Agentic AI meets Serverless on AWS

• In this talk we'll dive deep into various aspects of how Serverless and Agentic AI play together on AWS cloud. We'll explore Amazon Bedrock AgentCore Gateway which transforms existing APIs and AWS Lambda functions into agent-ready tools, offering unified access across protocols, including MCP, and runtime discovery. We'll also explore Strands Agents and how to use it to interact with AgentCore Gateway. Strands Agents is an open source SDK that takes a model-driven approach to building and running AI agents in just a few lines of code. We'll deploy our agent with the help of Amazon Bedrock AgentCore Runtime which provides a secure, serverless and purpose-built hosting environment for deploying and running AI agents or tools and look at the Observability and Memory features of the AgentCore.

Meet Vadym:

• Vadym Kazulkin is AWS Serverless Hero and Head of Development at ip.labs based in Bonn. Vadym has been involved with the Java ecosystem for over 25 years. His focus and interests currently include the design and implementation of highly scalable and available applications in AWS Cloud with the special passion for Serverless, Generative AI and optimization of Java applications (also using SpringBoot, Micronaut and Quarkus frameworks) on AWS Lambda. Vadym is also the co-organizer of the Java User Group Bonn meetup, a frequent speaker at various meetups and conferences and a regular author of the articles in the different published magazines and on his online blog.

LinkedIn: https://www.linkedin.com/in/vadymkazulkin/