About Me

I'm Ashish Bhutani, a backend engineer working on AI products and infrastructure. Most of my career has been in backend systems and ML infrastructure, and lately I've been spending more time with GenAI, particularly around LLM serving and inference.

What this blog is about

I write about the things I'm learning as I go. The posts cover how LLM serving systems work under the hood, the trade-offs that come up when you try to run them in production, and the engineering decisions behind them. I try to keep things practical and grounded in how systems actually behave, not how they look in a slide deck.

Why I write this

Writing helps me learn. When I try to explain something clearly, I find the gaps in my own understanding. This blog is mostly for that. If other engineers find it useful along the way, even better.