Stream All Things - Patterns of Data Stream Processing
Data streaming is a really difficult problem. We know this because 80% of the time in every project is spent optimizing the streaming data and analyzing windows. We know this because this problem remains challenging despite 10+ years of attempts to solve it. All we want is a service that will be reliable, handle all kinds of data and connect with all kinds of systems, be easy to manage and scale as our systems grow. Oh, and it should be super low latency too. Is it too much to ask?
In this presentation, we’ll discuss the basic challenges of data streaming and introduce a few design and architecture patterns that are used to tackle these challenges. We will then explore how these patterns can be implemented using Apache Flink. Difficult problems are difficult and we offer no silver bullets, but we will share pragmatic solutions that helped many organizations build fast, scalable and manageable data streaming pipelines.
Unleashing the Power of Grassroots Adoption: Revolutionizing DevRel with Political Insights
Envision a world where innovation thrives on the collective wisdom of the masses, where the voices of end-users shape the very destiny of products. A world where grassroots adoption and a bottom-up growth model unite, blazing a trail toward unparalleled success.
In this extraordinary convergence, end-users take center stage, transcending the limited influence of top-down leadership decisions. Even when products are procured by executives, the true key lies in captivating the hearts and minds of a high-performing team of software engineers—a dynamic force fueled by passion, engagement, and unwavering dedication not only to work with the product but to relentlessly enhance it.
Join me to embark on this new journey, exploring the powerful intersection of politics and DevRel. Delve into the essence of bottom-up adoption and embrace its potential for profound change.
Keynote: When Software Starts Talking to Itself
For decades, we’ve built messaging systems around a simple assumption: software receives an event, processes it, and produces a result. We’ve become remarkably good at making those systems reliable with ordering, retries, backpressure, state, replay, and failure recovery.
But what happens when the consumer is no longer a deterministic service?
AI agents can interpret events, make decisions, call tools, create new work, communicate with other agents, and change their behaviour based on what they observe. A single message can now trigger an unpredictable chain of actions across a distributed system.
This changes the meaning of some of our most fundamental guarantees.
In this keynote, we’ll explore how agentic systems are reshaping the distributed-systems problems we thought we had already solved, and why messaging infrastructure may become the critical coordination layer for autonomous software.
The future of messaging isn't just about moving data.
How Do You Get AI Into Production?
In the ever-evolving landscape of technology and Generative AI, integrating DevOps principles into the machine learning (ML) lifecycle is a transformative game-changer. The challenges of deploying, utilizing, and monitoring ML models in production require specialized attention.
Join me for an insightful session where we will explore essential aspects such as mlflow, deployment patterns, and monitoring techniques for ML models. Gain a deeper understanding of how to effectively navigate the complexities of deploying ML models into production environments. Discover best practices and proven strategies for monitoring and observing ML models in real-world scenarios.
By attending this session, you will acquire valuable insights and practical knowledge to overcome the unique hurdles of scaling and bringing AI into production. Unlock the full potential of your ML models by embracing the powerful integration of DevOps principles. This presentation is based on the extensive customer research I conducted to write the Best Seller book - Scaling Machine Learning with Spark - https://www.amazon.com/Scaling-Machine-Learning-Spark-Distributed/dp/1098106822.
Bursty workload - cutting costs with Kubernetes, Virtual Kublet and ACI
By running your workloads in Azure Kubernetes Service (AKS), you can focus on designing and building your applications instead of managing the infrastructure that runs them.
But wait! what about the cost?? When running containers in AKS, you are charged by the second for each container, even when it's idle.
However, with the Virtual Kubelet provider for Aks and Azure Container Instances, both Linux and Windows containers can be scheduled on a container instance as if it is a standard Kubernetes node. This configuration allows you to take advantage of both the capabilities of Kubernetes and the management value and cost-benefit of container instances.
In this talk you will learn how to deploy an application to Aks and ACI with Virtual Kublet. While leveraging the scalability of Kubernetes and cost efficiency of ACI.
An Offer You Can't Refuse: Discovering Chicago Film Sets with MLOps in Kubernetes
Lights, camera, Kubernetes! Join us to explore buzzing film sets and shooting locations in Chicago, the film-rich city. In this session, we combine Kubernetes, open-source ML tools, and open data to help you choose the perfect film set to visit. By utilizing real-world datasets like Filming Permits from the City of Chicago's Transportation Department, we reveal the potential of Kubernetes and CNCF projects for data-driven applications.
Discover design patterns and best practices for integrating Kubernetes and CNCF projects into your app stack seamlessly. By the end, you'll have the knowledge and tools to create MLOps workflows and find the best spots to experience your favorite films.
Get ready for a journey where Kubernetes empowers film enthusiasts, unlocking the magic of film sets while mastering modern app development. As the Godfather would say, "Deploying Kubernetes: An offer you can't refuse."
CI/CD with an Idempotent Kafka Producer & Consumer
Idempotence is a mathematical requirement of particular operations where the operation can be applied multiple times without changing the result beyond the initial application.
The main driver behind the idempotency requirement is often to handle duplicated messages. As developers and architects, we need to pay close attention to how we deal with our production data during new deployments to ensure we are not losing any data, duplicating messages, or introducing malformed data into our system. Furthermore, we need to figure out how to automate the process and add testing guarantees to prevent any potential human error.
In this session, you will learn about the idempotent Kafka Producer & Consumer architecture and how to automate the CI/CD process with open-source tools.
DevRel Experience 2023 Sessionize Event
DevOps Vision 2023 Sessionize Event
Current 2022: The Next Generation of Kafka Summit Sessionize Event
Kafka Summit London 2022 Sessionize Event
SQLBits 2022 Sessionize Event
CDC 2021 Sessionize Event
CloudBrew 2019 - A two-day Microsoft Azure event Sessionize Event
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top