Aakash Madabhushi
I build applications on top of language models, with retrieval that grounds them and gates that stop them acting alone.
Retrieval-grounded systems are the core of it: a Pinecone index of CVE and MITRE ATT&CK material feeding Llama 3.3 to explain why a network link was flagged, returning an analyst-readable answer in under a second; and a scheduled pipeline that embeds articles so they can be searched by meaning rather than keyword.
The agent work takes a consistent stance, which is that a person approves before anything irreversible happens. InvoSense scores its own confidence on each extracted field and blocks every payment action pending human review. The LinkedIn recruiting assistant takes a recruiter from résumé to outreach but pauses before it sends. Reader runs its model on-device, so nothing you read leaves your machine. I have also worked a layer below the framework, having written a GPT-2 and a byte-pair tokenizer from scratch, sped up attention, and fine-tuned Phi-3 into a chat assistant. I ran a LangChain workshop series for SJSU’s AI/ML Club.
Every link goes to code or data you can inspect yourself.
Reads a photo of an invoice, pulls out the amounts and dates, and scores its own confidence in each field. It refuses to record a payment until a person approves it.
Personal project · Jun 2026
Watches APIs for trouble, asks an LLM what went wrong, and takes corrective action. It tunes its own alert thresholds from what happened last time. Built in five hours.
SJSU Applied Data Science Hackathon 2026 · Mar 2026
A LinkedIn-style hiring platform running as 17 coordinated services, plus an AI assistant that takes a recruiter from résumé to outreach and pauses for human approval before it sends anything.
SJSU DATA 236, Distributed Systems · Spring 2026
A Chrome extension and companion iOS app that help you finish what you start. The AI runs on your own machine, so nothing you read ever leaves it.
Personal project · Jul 2026 to present
Condensed 27 million raw network connection logs into a map of which machines talked to each other, flagged the suspicious pairs with a graph neural network, and had a language model explain every alert in plain English.
SJSU capstone, team project · Feb to May 2026
A scheduled pipeline that converts articles into vectors and makes them searchable by meaning rather than exact keywords.
I'm available from December 2026 and open to relocating. Email me and I'll reply within a day.
Hiring for something else?