# Anush Deokar

> Anush Deokar is a Full Stack + AI Engineer and founding AI engineer at Meridian, building RAG pipelines, MCP servers, and multi-agent chat and voice systems end to end. Also runs from-scratch LLM architecture experiments and writes them up.

I'm a founding AI engineer at Meridian, where I build the core AI platform end to end: RAG pipelines and MCP servers underneath, multi-agent flows in the middle, and the chat and voice agents people actually talk to on top. Before that I spent years as a frontend and full-stack engineer, so I own the whole path, from raw data to the interface.

Outside work I run experiments and build side projects: taking ideas apart, testing them carefully, and writing up what I learn.

## About

- [Profile, experience and projects](https://www.anushdeokar.xyz/index.md): roles, what was built at each, skills, education and projects
- [Everything in one file](https://www.anushdeokar.xyz/llms-full.txt): the profile plus the full text of every post

## Experience

- Founding AI Engineer, Meridian (Jun 2025 – Present): Founding engineer on the AI platform behind Meridian's products, designing systems end to end, from ingestion and retrieval to multi-agent flows in production.
- Software Engineer, Trek Health (Mar 2024 – Present): Led core development on turning terabytes of complex healthcare data into accessible, actionable insights for clients.
- Software Engineer, matrice.ai (Jul 2023 – Apr 2024): Led and maintained the main product's React + TypeScript frontend, and backend microservices for image annotation.

## Projects

- [Tiny Frontier](https://github.com/AnushDeokar/tiny-frontier): How do modern LLMs keep memory cheap? I'm rebuilding sliding-window attention and attention sinks from scratch, testing them with controlled multi-seed experiments, all on a $0 compute budget.
- [Typeform clone](https://github.com/AnushDeokar/typeform-clone): Form builder with workspaces and publishing, server actions and zod validation. 100+ users.
- [Csgrid](https://github.com/AnushDeokar/Csgrid): Blogging platform with cover uploads, tags, and search and filtering by tag.

## Writing: Tiny Frontier

- [Part 1: Shrinking the frontier: rebuilding modern LLM tricks from scratch](https://www.anushdeokar.xyz/writing/tiny-frontier/background.md): The question, the rules for fair comparisons, a 3.4M-parameter control model, and proving the code is right by matching Google's Gemma 3 270M.
- [Part 2: How small can attention windows get?](https://www.anushdeokar.xyz/writing/tiny-frontier/local-global-attention.md): Sliding windows, local:global layer patterns, and what they cost in quality versus what they save in KV-cache memory.
- [Part 3: Attention sinks and streaming](https://www.anushdeokar.xyz/writing/tiny-frontier/attention-sinks.md): Streaming 16× past the training length with a 64-token cache. The predicted collapse didn't happen, and one controlled run showed why: sinks come from the training data format.

## Optional

- Website: https://www.anushdeokar.xyz
- GitHub: https://github.com/AnushDeokar
- LinkedIn: https://www.linkedin.com/in/anushdeokar/
- X: https://x.com/AnushDeokar
- Email: deokaranush@gmail.com