PyData Berlin
Building Bridges, Not Silos: Lessons from Running a Data & ML/AI Engineering community at Vattenfall
Talk
Abstract
In large organizations, data and AI talent often work in fragmented teams, making cross-pollination of ideas, tools, and best practices a challenge. At Vattenfall, we addressed this by founding the “Data & ML/AI Engineering Guild” — a cross-functional community dedicated to sharing knowledge, aligning on technical standards, and accelerating innovation across business units.
Prerequisites
NA
Description
As data professionals, we talk a lot about breaking down data silos — but the reality is, silos exist not just in our data, but in our teams. At Vattenfall, data and ML/AI engineers are spread across different units, projects, and domains. We often face similar challenges, reinvent similar solutions, and learn the hard way: in parallel, and in isolation.
To address this, we started something simple but powerful: a community. The "Data & ML/AI Engineering Guild" began as a small group of engineers coming together to share learnings and frustrations. Over time, it evolved into a cross-functional space where we exchange knowledge, run internal talks, and build technical momentum across the organization.
In this talk, I’ll walk through how we built and scaled this guild: what worked, what didn’t, and what we’re still figuring out. I’ll share the formats we use to keep engagement high (even when calendars are packed), how we balance deep technical discussions with accessibility. I’ll also reflect on how this kind of community work complements our day jobs, and how it helps engineers grow beyond the boundaries of their product teams.
If you’re thinking about starting a tech guild, already running one, or just curious how to create more connection and consistency in your data/ML org, this talk is for you. My goal is to share honest lessons (not just success stories) and hopefully spark ideas you can adapt in your own context.
Speaker
Anastasia Karavdina
Solutions Architect ML/AI & BI
My background is particle physics, where I was completely spoiled by access to large amounts of data and the freedom to try out every hot ML algorithm on it. The experiments I participated in were so-called large scale experiments (e.g Large Hadron Collider) and had from 500+ up to 2.5k other people working on them. So in addition to physics, I was exposed to the best software development practices that helped us to avoid a complete mess and destroy the Universe. Afterwards I was working as Data Scientist in various fields and recently became "Solution Architect ML/AI and BI" at big enterprise company. During my free time, I like learning new tools and techniques and implementing them in end-to-end AI/ML and IoT projects. My experience has also been very helpful in guiding data analysts, data scientists, and machine learning engineers as a mentor and contributing to the growth of the next generation of data scientist elite.