Tech Lead |Software Architecture & Production Systems

Most AI learning roadmaps are built for people starting from zero. This one is built for someone who already knows how production systems fail, and wants to apply that instinct to enterprise AI without wasting 18 months on the wrong things.

I transitioned from Analytical Chemistry to AI after a PhD studying PAH detection. Here's how scientific thinking and the use of AI in Chemistry shaped how I learn Artificial Intelligence.

I came into RAG with strong production architecture instincts and assumed they'd transfer cleanly. Some did. The places where they didn't are where I made my biggest mistakes — and where most teams I've talked to are making theirs.

Discover why a seasoned tech lead decided to dive into the world of Artificial Intelligence. In this post, I share the mindset shift, learning roadmap, and career goals behind my journey from mobile development to AI — and how you can start yours too.

Enterprise software is built on determinism. AI systems are fundamentally probabilistic. That mismatch is the root cause of most enterprise AI reliability failures — and closing it requires a different mental model, not just better engineering.

Enterprise software is built on determinism. AI systems are fundamentally probabilistic. That mismatch is the root cause of most enterprise AI reliability failures — and closing it requires a different mental model, not just better engineering.

RAG is the right pattern for enterprise AI. That doesn't mean it's easy to get right. Here are the failure modes that production systems actually hit — and what to do about them before they reach your users.

Most RAG systems ship without the instrumentation to know whether they're working. Not because the teams are careless — because the metrics aren't obvious and the tooling isn't mature. Here's what you actually need to measure before a RAG system goes live, and why skipping it makes every subsequent problem harder to diagnose.