Sarthak Agrawal · AI Infrastructure & Product Engineer
I build dependable AI products, from infrastructure to interface.
I'm Sarthak Agrawal, an AI infrastructure and product engineer. CodeVetter and PostTrainLLM are my primary focus; the latter is a public research lab, and SaaS Maker keeps the wider directory and shared workshop visible.
Open to AI infra & product roles
// current focus
Working experiments you can explore.
PostTrainLLM offers a working browser model playground. SaaS Maker lists the experiments and reference projects with a useful public surface.
- CodeVetter
- Execution-backed verification for AI-written software changes — local-first and inspectable. https://codevetter.com
- PostTrainLLM
- An experimental browser model playground: run small language models locally with visible generation metrics. https://posttrainllm.com
- SaaS Maker
- A public directory of working experiments, launch destinations, reference projects and reusable tooling. https://sassmaker.com
// selected work
A few things I've built.
5 projects from my professional and personal work — what the problem was, what I built, and what changed.
PostTrainLLM — a transformer built end to end, then a local LLM factory
A small GPT (~0.8M params, byte-level) written from scratch in three layers — a PyTorch reference, a hand-derived C++/WASM implementation, and a full WebGPU training loop — running entirely in a browser tab. Every layer's backward pass was finite-difference checked before being trusted. It has since grown into a Mac-first LLM factory and runtime, where a 4B model distilled from ~99 frontier rollouts scored 100% on a hard multi-turn tool-calling gate.
Vector-Powered Personalized Feeds
A home feed that actually learns what you like. Content gets embedded with BERT, ranked by similarity in Milvus, and the user vector keeps updating from live events. Engagement went up 40%.
Real-Time Market Data Pipeline
The streaming backbone of a fintech social app. Go services stream live market data through Kafka, and Socket.IO delivers real-time ticks to clients — and it held up while daily users went from 15k to 200k.
RAG Agents for Support & Learning
A set of RAG chatbots — support, learning, assistant — built on OpenAI APIs and grounded in real product docs, plus a moderation bot that cut human intervention in support queries by 90%.
Durable Financial Workflows
Financial planning can't run on workflows that quietly break. Moving them to Temporal killed 90% of the random failures and gave the team back about three hours a day.
SaaS Maker
A public directory of working experiments, reference projects and reusable tooling.