Engineer. Builder. Occasional writer.
Working at the intersection of AI, product, and software. Currently building at Tekvo and Milao.
Writing All posts →
Building Llama 3.2 From Scratch (How Modern LLMs Improved on GPT-2) Week 2 of the model-atlas series: rebuild a Llama-style decoder block in PyTorch and see why RoPE, RMSNorm, GQA, and SwiGLU became the modern default.
→ Building GPT-2 From Scratch (and Loading Real Weights) Week 1 of a 24-model series: implement every layer in PyTorch, load OpenAI's checkpoint, and see why today's LLMs are still this architecture.
→ Seven Hidden Faults in Every Tamil NLP Pipeline Unicode fragmentation, mojibake, agglutination explosions, and the romanized web your model never saw - a field audit of what goes wrong before training.
→ Building a Tiny Tamil GPT From Scratch What I learned training a decoder-only Transformer on my own data
→ The Anatomy of an RL Environment — How AI Agents Actually Learn to Write Better Code Most people think training an AI agent is about feeding it data and hoping it gets smarter. It's not. Here's what a real RL environment looks like under the hood.
→ Projects All →
Founder OS
A personal operating system for founders — knowledge management, task tracking, and decision-making in one place.
Milao
AI-powered platform that helps students and professionals improve communication through speech intelligence, personalized feedback, and guided learning workflows.
This site
My personal site — blog, project showcase, and digital garden. Built with Astro.