Medaura - Agentic Pharmacy System
Medication errors are an information problem. The information exists - it is just not connected at the moment it matters.
FastAPILangGraphChromaDBLangfuseReact
AI Engineer & Researcher
I keep digging into rabbit holes, some become systems.
- Recently
- LFX'26 @ Hyperledger Cello
- Active contributor to Meshery (CNCF)
- Researching and prototyping domain-specific small language models
Background & focus
About
I started in RF and signals. Turns out the most interesting signal to decode is language. Now I build the systems that do both — from transformers to multi-agent pipelines to LLM-controlled hardware.
B.Tech — Electronics & Telecom Engineering at SGGSIE&T, Nanded (2023–Present).
Achievements
- National Finalist — Smart India Hackathon 2024
- National Finalist — Smart India Hackathon 2025
- Global Finalist Top 6 — UWA Hack For Impact 2026
Research & engineering
Experience
Jun 2026 – Present
LFX Mentee
Hyperledger Cello · Linux Foundation
Building an AI agent that turns Hyperledger Fabric network operations and Chaincode debugging into a conversation.
- Designing an AI agent that takes natural language, reasons over Cello API call sequences, and executes operations — eliminating manual dashboard interaction
- Hyperledger Cello manages the full lifecycle of Hyperledger Fabric networks
Apr 2026 – Present
AI Research Intern
IRT, University of South Carolina
Researching neurosymbolic SLM architectures with RL-based alignment.
- Researching neurosymbolic SLM architecture and pre-training pipelines — integrating symbolic reasoning constraints into small language model training for structured knowledge tasks
- Working on RL-based fine-tuning (GRPO/RLHF) for SLM alignment — reward modeling, policy optimization, and evaluation on neurosymbolic reasoning benchmarks
Mar 2026 – Present
Open Source Contributor
Meshery — CNCF Sandbox Project
5+ merged PRs across service mesh management, UI, and API integrations.
- 5+ merged PRs — service mesh management features, UI components, and API integrations across Go backend and React frontend
- Active in code reviews, issue triage, and community discussions per CNCF contributor guidelines
Selected work
Projects
Small Language Model From Scratch - TinyStories
Every LLM course teaches you to call an API. I wanted to know what happens before the API.
PyTorchCustom BPEAMPNLP
03
GNU Radio MCP Server - LLM-to-SDR Bridge
LLMs can reason about RF signals. They just could not touch a radio. This closes that gap.
PythonFastMCPZMQXML-RPCGNU Radio
RF Watch - Open-Source Real-Time RF Spectrum Monitor
Physical-layer first: no protocol decoding, no black-box certainty, just traceable RF evidence.
PythonGNU RadioHackRF OneSignal Processing
Papers & interests
Research
Reading and building on foundational ML research. Here are papers that shaped my thinking.
01arXiv
ReAct: Synergizing Reasoning and Acting
Agents observe before they act.
2210.0362902arXiv
Toolformer: Models Teach Themselves to Use Tools
The mental model for LLMs using external tools.
2302.0476103arXiv
Switch Transformers: Mixture of Experts
Modular capacity beats monolithic scaling.
2101.0396104arXiv
Group Relative Policy Optimization
A foundation for post-training interest.
2402.0330005arXiv
Direct Preference Optimization
Preference optimization without treating RL as magic.
2305.1829001arXiv
ReAct: Synergizing Reasoning and Acting
Agents observe before they act.
2210.0362902arXiv
Toolformer: Models Teach Themselves to Use Tools
The mental model for LLMs using external tools.
2302.0476103arXiv
Switch Transformers: Mixture of Experts
Modular capacity beats monolithic scaling.
2101.0396104arXiv
Group Relative Policy Optimization
A foundation for post-training interest.
2402.0330005arXiv
Direct Preference Optimization
Preference optimization without treating RL as magic.
2305.18290Get in touch
Contact
Currently interested in AI research internships, open-source collaborations, and systems engineering opportunities.
Not everything is meant to be but everything is worth trying