Senior Engineer · Infra, AI & Systems
Writing about infrastructure, distributed systems, scaling, and AI research. Building things that work at scale.
No fine-tuning. No LoRA. No base model. Training a 7 billion parameter language model from random weights, on rented H100s. General-purpose first, then specialized for code through SFT and RL on real agent trajectories.
How to build a chat system where multiple specialized AI agents handle different types of requests instead of one agent trying to do everything.
When your AI operation takes 30+ seconds, you cant just show a spinner. Here is how to use Server-Sent Events to stream progress in real time.
How I added Claude Code-style team coordination to Codex — one lead agent spawning and coordinating multiple teammates in parallel using a shared filesystem task board.
How I built a reusable chat component library with React 19 and Vite that works across multiple projects.
First post on abhishek.it.