Recent Writing

Understanding SnapKV: Compressing LLM Memory From First Principles Tue Jun 23 2026

Understanding QTIP & QUIP Quantization: Shaping Error to Save Memory Sun Jun 21 2026

Understanding LLM.int8(): Making Large Models Fit Fri Jun 12 2026

Understanding Flash Attention: Making Transformers Fast Tue Jun 09 2026

Transformer Architecture: From First Principles Mon Jun 08 2026

Ankit Mishra

I build software and A.I products from 0 -> 1, move fast, and thrive in high-ownership environments where initiative matters.

Links: [GitHub] [Twitter] [LinkedIn]

Founding AI Engineer at DocuraHealth (YC W26), ex-MLE at Pibit.ai (YC W21), and ex-Founding AI Engineer at AarogyaID . During college, I worked across 5 startups and an open-source organization as an AI & Software Engineer and also taught as a Python Instructor at USF.

Building agentic software that creates real-world value.

THE MATH THAT BENT THE TRAJECTORY OF AI

Attention(Q, K, V) = softmax(QK^T/√d_k)V

Lex Fridman — Go All The Way (Charles Bukowski) 0:00

Core Philosophy

Curiosity should always reach below the abstraction layer.

I enjoy breaking down complex systems into first principles, understanding how they work, and building on that foundation rather than treating technology as a black box.

Recent Writing

Ankit Mishra

Core Philosophy

Directory