Send us a text In this episode, we're joined by Sam Debruyn and Dorian Van den Heede who reflect on their talks at SQL Bits 2025 and dive into the technical content they presented. Sam walks through how dbt integrates with Microsoft Fabric, explaining how it improves lakehouse and warehouse workflows by adding modularity, testing, and documentation to SQL development. He also touches on Fusion’s SQL optimization features and how it compares to tools like SQLMesh. Dorian shares his MLOps demo, which simulates beating football bookmakers using historical data,nshowing how to build a full pipeline with Azure ML, from feature engineering to model deployment. They discuss the role of Python modeling in dbt, orchestration with Azure ML, and the practical challenges of implementing MLOps in real-world scenarios. Toward the end, they explore how AI tools like Copilot are changing the way engineers learn and debug code, raising questions about explainability, skill development, and the future of junior roles in tech. It’s rich conversation covering dbt, MLOps, Python, Azure ML, and the evolving role of AI in engineering.

Raluca Crisan, CTO, etiq.ai — Coding assistants are not quite enough for Data science or ML work, they don’t quite solve the right kind of problems. However they are undeniably helpful. In this talk we explain how combining coding assistants and elements from MLOps can unlock immense potential value for the space.

As AI adoption accelerates across industries, many organisations are realising that building a model is only the beginning. Real-world deployment of AI demands robust infrastructure, clean and connected data, and secure, scalable MLOps pipelines. In this panel, experts from across the AI ecosystem share lessons from the frontlines of operationalising AI at scale.

We’ll dig into the tough questions:

• What are the biggest blockers to AI adoption in large enterprises — and how can we overcome them?

• Why does bad data still derail even the most advanced models, and how can we fix the data quality gap?

• Where does synthetic data fit into real-world AI pipelines — and how do we define “real” data?

• Is Agentic AI the next evolution, or just noise — and how should MLOps prepare?

• What does a modern, secure AI stack look like when using external partners and APIs?

Expect sharp perspectives on data integration, model lifecycle management, and the cyber-physical infrastructure needed to make AI more than just a POC.

The rapid evolution of AI, fueled by powerful Large Language Models (LLMs) and autonomous agents, is reshaping how we build, deploy, and manage AI systems. This presentation explores the critical intersection of MLOps and AI architecture, highlighting the paradigm shifts required to integrate LLMs and agents into production. We will address key architectural challenges, including scalability, observability, and security, while examining emerging MLOps practices such as robust data pipelines, model monitoring, and continuous optimization. Attendees will gain practical insights and actionable strategies to navigate the complexities of modern AI deployments, unlocking the full potential of LLMs and agents while ensuring operational excellence.

As AI evolves with powerful Large Language Models (LLMs) and autonomous agents, deploying and managing these systems requires new approaches. This presentation explores the crucial intersection of MLOps and AI architecture, highlighting the shift toward scalable, observable, and secure AI deployments. We’ll examine key architectural considerations for integrating LLMs and agents into production, alongside evolving MLOps practices such as robust data pipelines, model monitoring, and continuous optimization.

Development teams often embrace Agile ways of working, yet the systems we build can still struggle to adapt when business needs shift. In this talk, we’ll share the journey of how a cross-functional data science team at the LEGO Group evolved its machine learning architecture to handle real-world complexity and change.

We’ll highlight how new modelling strategies, advanced feature engineering, and modern MLOps pipelines were designed not only for performance, but for flexibility. You’ll gain insight into how we architected a resilient ML system that supports changing requirements, scales with ease, and enables faster iteration. Expect actionable ideas on how to future-proof your own ML solutions and ensure they remain relevant in dynamic business contexts.

Powered by: Women in Data®

This talk explores the disconnect between MLOps fundamental principles and their practical application in designing, operating and maintaining machine learning pipelines. We’ll break down these principles, examine their influence on pipeline architecture, and conclude with a straightforward, vendor-agnostic mind-map, offering a roadmap to build resilient MLOps systems for any project or technology stack. Despite the surge in tools and platforms, many teams still struggle with the same underlying issues: brittle data dependencies, poor observability, unclear ownership, and pipelines that silently break once deployed. Architecture alone isn't the answer; systems thinking is.

Topics covered include:

- Modular design: feature, training, inference

- Built-in observability, versioning, reuse

- Orchestration across batch, real-time, LLMs

- Platform-agnostic patterns that scale

This talk explores the disconnect between MLOps fundamental principles and their practical application in designing ML Pipelines.

Keynote talk by Demetrios Brinkmann, Chief Vibe Officer at MLOps Community.

As models grow in complexity, how can we ensure reliable, cost-efficient hosting at scale?

What does AI transformation really look like inside a 180-year-old company? In this episode of Data Unchained, we are joined by Younes Hairej, founder and CEO of Aokumo Inc, a trailblazing company helping enterprises in Japan and beyond bridge the gap between business intent and AI execution. From deploying autonomous AI agents that eliminate the need for dashboards and YAML, to revitalizing siloed, analog systems in manufacturing, Younes shares what it takes to modernize legacy infrastructure without starting over. Cyberpunk by jiglr | https://soundcloud.com/jiglrmusic Music promoted by https://www.free-stock-music.com Creative Commons Attribution 3.0 Unported License https://creativecommons.org/licenses/by/3.0/deed.en_US

ArtificialIntelligence #EnterpriseAI #AITransformation #Kubernetes #DevOps #GenAI #DigitalTransformation #OpenSourceAI #DataInfrastructure #BusinessInnovation #AIInJapan #LegacyModernization #MetadataStrategy #AIOrchestration #CloudNative #AIAutomation #DataGovernance #MLOps #IntelligentAgents #TechLeadership

Hosted on Acast. See acast.com/privacy for more information.

Send us a text Welcome to the cozy corner of the tech world! Datatopics is your go-to spot for relaxed discussions around tech, news, data, and society. In this episode of Data Topics, we sit down with Nick Schouten — data engineer at dataroots — for a full recap of KubeCon Europe 2025 and a deep dive into the current and future state of Kubernetes. We talk through what’s actually happening in the Kubernetes ecosystem — from platform engineering trends to AI infra challenges — and why some teams are doubling down while others are stepping away. Here’s what we cover: What Kubernetes actually is, and how to explain it beyond the buzzwordWhen Kubernetes is the right choice (e.g., hybrid environments, GPU-heavy workloads) — and when it’s overkillHow teams are trying to host LLMs and AI models on Kubernetes, and the blockers they’re hitting (GPUs, complexity, cost)GitOps innovations spotted at KubeCon — like tools that convert UI clicks into Git commits for infrastructure-as-codeWhy observability is still one of Kubernetes’ biggest weaknesses, and how a wave of new startups are trying to solve itThe push to improve developer experience for ML and data teams (no more YAML overload)The debate around abstraction vs control — and how some teams are turning away from Kubernetes entirely in favor of simpler toolsWhat “vibe coding” means in an LLM-driven world, and how voice-to-code workflows are changing how we write infrastructureWhether the future of Kubernetes is more “visible and accessible,” or further under the hoodIf you're a data engineer, MLOps practitioner, platform lead, or simply trying to stay ahead of the curve in infrastructure and AI — this episode is packed with relevant insights from someone who's hands-on with both the tools and the teaching.

Send us a text Welcome to the cozy corner of the tech world! Datatopics is your go-to spot for relaxed discussions around tech, news, data, and society. This week, co-host Ben is joined by Jackie Janssen, former Chief Data Officer at CM, author of AI: De Hype Voorbij, and an evangelist for pragmatic, human-centered AI. Together, they trace the winding path from early tech roles to enterprise transformation, exploring how AI can actually serve humans (and not just the hype machine). In this episode: Leadership in AI transformation: From KBC to CM, lessons on creating cultural buy-in.Building effective data teams: Why the first hire isn’t always a data engineer.AI governance: What makes a strong AI Council and why CEOs should care.Product and process thinking: How MLOps, data factories, and product mindsets intersect.Agents and autonomy: The future of work with AI teammates, not just tools.The human edge in a machine world: A preview of Jackie’s next book on rediscovering humanity in the age of AI.Curious about Jackie’s take on AI agents, cultural inertia, or what really makes a great data strategy tick? Tune in, you might just find a new way to think about your tech stack and your team.

In legacy Airflow 2.x, each DAG run was tied to a unique “execution_date.” By removing this requirement, Airflow can now directly support a variety of new use cases, such as model training and generative AI inference, without the need for hacks and workarounds typically used by machine learning and AI engineers. In this talk, we will delve into the significant advancements in Airflow 3 that enable GenAI and MLOps use cases, particularly through the changes outlined in AIP 83. We’ll cover key changes like the renaming of “execution_date” to “logical_date,” along with the allowance for it to be null, and the introduction of the new “run_after” field which provides a more meaningful mechanism for scheduling and sorting. Furthermore, we’ll discuss how Airflow 3 enables multiple parallel runs, empowering diverse triggering mechanisms and easing backfill logic with a real-world demo.

As your organization scales to 20+ data science teams and 300+ DS/ML/DE engineers, you face a critical challenge: how to build a secure, reliable, and scalable orchestration layer that supports both fast experimentation and stable production workflows. We chose Airflow — and didn’t regret it! But to make it truly work at our scale, we had to rethink its architecture from the ground up. In this talk, we’ll share how we turned Airflow into a powerful MLOps platform through its core capability: running pipelines across multiple K8s GPU clusters from a single UI (!) using per-cluster worker pools. To support ease of use, we developed MLTool — our own library for fast and standardized DAG development, integrated Vault for secure secret management across teams, enabled real-time logging with S3 persistence and built a custom SparkSubmitOperator for Kerberos-authenticated Spark/Hadoop jobs in Kubernetes. We also streamlined the developer experience — users can generate a GitLab repo and deploy a versioned pipeline to prod in under 10 minutes! We’re proud of what we’ve built — and our users are too. Now we want to share it with the world!

Airflow 3 brings several exciting new features that better support MLOps: Native, intuitive backfills Removal of the unique execution date for dag runs Native support for event-driven scheduling These features, combined with the Airflow AI SDK, enable dag authors to easily build scalable, maintainable, and performant LLMOps pipelines. In this talk, we’ll go through a series of workflows that use the Airflow AI SDK to empower Astronomer’s support staff to more quickly resolve problems faced by Astronomer’s customers.

This talk explores EDB’s journey from siloed reporting to a unified data platform, powered by Airflow. We’ll delve into the architectural evolution, showcasing how Airflow orchestrates a diverse range of use cases, from Analytics Engineering to complex MLOps pipelines. Learn how EDB leverages Airflow and Cosmos to integrate dbt for robust data transformations, ensuring data quality and consistency. We’ll provide a detailed case study of our MLOps implementation, demonstrating how Airflow manages training, inference, and model monitoring pipelines for Azure Machine Learning models. Discover the design considerations driven by our internal data governance framework and gain insights into our future plans for AIOps integration with Airflow.

The journey from ML model development to production deployment and monitoring is often complex and fragmented. How can teams overcome the chaos of disparate tools and processes? This session dives into how Apache Airflow serves as a unifying force in MLOps. We’ll begin with a look at the broader MLOps trends observed by Google within the Airflow community, highlighting how Airflow is evolving to meet these challenges and showcasing diverse MLOps use cases – both current and future. Then, Priceline will present a deep-dive case study on their MLOps transformation. Learn how they leveraged Cloud Composer, Google Cloud’s managed Apache Airflow service, to orchestrate their entire ML pipeline end-to-end: ETL, data preprocessing, model building & training, Dockerization, Google Artifact Registry integration, deployment, model serving, and evaluation. Discover how using Cloud Composer on GCP enabled them to build a scalable, reliable, adaptable, and maintainable MLOps practice, moving decisively from chaos to coordination. Cloud Composer (Airflow) has served as a major backbone in transforming the whole ML experience in Priceline. Join us to learn how to harness Airflow, particularly within a managed environment like Cloud Composer, for robust MLOps workflows, drawing lessons from both industry trends and a concrete, successful implementation.