Escaping Nulliverse
What if we could create a social network with no humans involved at all? And we'll build a company for it that won't employ any humans either. Then who is it for?
Engineering blog: data engineering, AI, software development, and team leadership.
I also offer data & AI engineering services.
What if we could create a social network with no humans involved at all? And we'll build a company for it that won't employ any humans either. Then who is it for?
The old hiring playbook is history. In the zombie shark infested lagoon of the 2026 hiring market, how do you find a great data engineer?
AI agents will happily dive into your data lake and produce exactly the right report. What they won't tell you is that data warehouses should more properly be called data mazes.
If you ask 10 executives which roles they need to run an AI adoption project, 9 of them won't mention data engineers. I believe this is a major reason why 80% of enterprise AI projects fail.
When you build an integration with an LLM provider and test it locally, everything usually looks fine. The problems start when you deploy the same code to a cloud environment.
How I combined elements of Hierarchical Task Network planning with LLMs to create a more consistent and flexible planning system.
Self-correction strategies where LLMs don't just generate content but actively review and refine their own outputs to fix errors autonomously.
LLMs can reason about complex input. They can also follow formatting instructions. But when asked to do both at once, they often fail. This post explains a two-step method that improves reliability.
When does a former startup start to feel corporate? What is culture, and what deserves to be written on the office walls?
The hiring manager interview is often a free-form conversation that candidates don't take seriously. That's a mistake. Here's how to make the most of it.
Defining data governance from first principles and explaining its place in the larger area of data management.
Next to technical expertise, the best engineers possess skills that amplify their impact. Let's talk about the 'soft' skills that aren't soft at all.
The concept of a 10x engineer sparked debates. But the real multiplier isn't coding speed — it's the team culture that amplifies everyone's impact.
A comprehensive list of skills that will get you a data engineering position and help you succeed in this role.
Why is there seemingly so much legacy everywhere you look? And is there something we can do to reduce the negative effect of legacy in our teams and companies?