In this podcast episode, we talked with Bartosz Mikulski about Data Intensive AI.

About the Speaker: Bartosz is an AI and data engineer. He specializes in moving AI projects from the good-enough-for-a-demo phase to production by building a testing infrastructure and fixing the issues detected by tests. On top of that, he teaches programmers and non-programmers how to use AI. He contributed one chapter to the book 97 Things Every Data Engineer Should Know, and he was a speaker at several conferences, including Data Natives, Berlin Buzzwords, and Global AI Developer Days. 

In this episode, we discuss Bartosz’s career journey, the importance of testing in data pipelines, and how AI tools like ChatGPT and Cursor are transforming development workflows. From prompt engineering to building Chrome extensions with AI, we dive into practical use cases, tools, and insights for anyone working in data-intensive AI projects. Whether you’re a data engineer, AI enthusiast, or just curious about the future of AI in tech, this episode offers valuable takeaways and real-world experiences.

0:00 Introduction to Bartosz and his background 4:00 Bartosz’s career journey from Java development to AI engineering 9:05 The importance of testing in data engineering 11:19 How to create tests for data pipelines 13:14 Tools and approaches for testing data pipelines 17:10 Choosing Spark for data engineering projects 19:05 The connection between data engineering and AI tools 21:39 Use cases of AI in data engineering and MLOps 25:13 Prompt engineering techniques and best practices 31:45 Prompt compression and caching in AI models 33:35 Thoughts on DeepSeek and open-source AI models 35:54 Using AI for lead classification and LinkedIn automation 41:04 Building Chrome extensions with AI integration 43:51 Comparing Cursor and GitHub Copilot for coding 47:11 Using ChatGPT and Perplexity for AI-assisted tasks 52:09 Hosting static websites and using AI for development 54:27 How blogging helps attract clients and share knowledge 58:15 Using AI to assist with writing and content creation

🔗 CONNECT WITH Bartosz LinkedIn: https://www.linkedin.com/in/mikulskibartosz/ Github: https://github.com/mikulskibartosz Website: https://mikulskibartosz.name/blog/

🔗 CONNECT WITH DataTalksClub Join the community - https://datatalks.club/slack.html Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ Check other upcoming events - https://lu.ma/dtc-events LinkedIn - https://www.linkedin.com/company/datatalks-club/ Twitter - https://twitter.com/DataTalksClub Website - https://datatalks.club/

Summary In this episode of the Data Engineering Podcast Bartosz Mikulski talks about preparing data for AI applications. Bartosz shares his journey from data engineering to MLOps and emphasizes the importance of data testing over software development in AI contexts. He discusses the types of data assets required for AI applications, including extensive test datasets, especially in generative AI, and explains the differences in data requirements for various AI application styles. The conversation also explores the skills data engineers need to transition into AI, such as familiarity with vector databases and new data modeling strategies, and highlights the challenges of evolving AI applications, including frequent reprocessing of data when changing chunking strategies or embedding models.

Announcements Hello and welcome to the Data Engineering Podcast, the show about modern data managementData migrations are brutal. They drag on for months—sometimes years—burning through resources and crushing team morale. Datafold's AI-powered Migration Agent changes all that. Their unique combination of AI code translation and automated data validation has helped companies complete migrations up to 10 times faster than manual approaches. And they're so confident in their solution, they'll actually guarantee your timeline in writing. Ready to turn your year-long migration into weeks? Visit dataengineeringpodcast.com/datafold today for the details. Your host is Tobias Macey and today I'm interviewing Bartosz Mikulski about how to prepare data for use in AI applicationsInterview IntroductionHow did you get involved in the area of data management?Can you start by outlining some of the main categories of data assets that are needed for AI applications?How does the nature of the application change those requirements? (e.g. RAG app vs. agent, etc.)How do the different assets map to the stages of the application lifecycle?What are some of the common roles and divisions of responsibility that you see in the construction and operation of a "typical" AI application?For data engineers who are used to data warehousing/BI, what are the skills that map to AI apps?What are some of the data modeling patterns that are needed to support AI apps?chunking strategies metadata managementWhat are the new categories of data that data engineers need to manage in the context of AI applications?agent memory generation/evolution conversation history managementdata collection for fine tuningWhat are some of the notable evolutions in the space of AI applications and their patterns that have happened in the past ~1-2 years that relate to the responsibilities of data engineers?What are some of the skills gaps that teams should be aware of and identify training opportunities for?What are the most interesting, innovative, or unexpected ways that you have seen data teams address the needs of AI applications?What are the most interesting, unexpected, or challenging lessons that you have learned while working on AI applications and their reliance on data?What are some of the emerging trends that you are paying particular attention to?Contact Info WebsiteLinkedInParting Question From your perspective, what is the biggest gap in the tooling or technology for data management today?Closing Announcements Thank you for listening! Don't forget to check out our other shows. Podcast.init covers the Python language, its community, and the innovative ways it is being used. The AI Engineering Podcast is your guide to the fast-moving world of building AI systems.Visit the site to subscribe to the show, sign up for the mailing list, and read the show notes.If you've learned something or tried out a project from the show then tell us about it! Email [email protected] with your story.Links SparkRayChunking StrategiesHypothetical document embeddingsModel Fine TuningPrompt CompressionThe intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA