- CS Undergraduate @ Arizona State University
- SWE @ ASU Decision Theatre | Prev ML Researcher @ RISE Lab
- Senior Officer @ Software Developers Association
- Experienced in building Internal Software Systems and ML pipelines
- Actively research and build LLMs & RL architectures
- Doc2MCP β API documentation to compressed MCP integration using agentic scraper (NexHacks '26)
- Piramid β Rust based Hybrid vector database for LLM agents with MCP support
- Kaelum β Reasoning Framework for Mixture of Expert LLM agents with Monte Carlo Tree Search
- AI Pedia β Headless CMS for managing AIS Wikis and resources (AIS)
- Godfather β Admin dashboard for managing shared runpod gpu sessions with custom CLI (AIS Internal)
- SparkyAI β Swarm of CRAG AI Agents work together on queries, take actions with self improving ML pipeline (ASU-Trusted)
- Agents & RAG from Scratch β Foundations of agentic collaboration and retrieval architectures (AIS Workshop)
- BenchMind β AI agent benchmarking evaluation + visualization (CalHacks S12 '25)
- RLHF from Scratch β PPO-based feedback optimization for LLMs (AIS Workshop)
- LLM from Scratch β Transformer-based LLM architectures built from fundamentals (AIS Workshop)
- Decoy β RAG-powered cyber intelligence pipeline (2x Google Hack Winner)
- SportSitters β Fullstack Chat, Voice/Video call, Booking Management iOS/android App with Admin CSM realtime Dashboard
- Platform β application integration for notion and google calendar API with faster lighthouse performance (SoDA)
- Eve β Gemini-powered robotic arm for multimodal equipment handling (PI Automation)
- Lux β Agentic AI for real-time fashion recommendations (Devhacks)
- AI Solar Panel β YOLOv8-based adaptive solar tracking system
- Carbon Emission Detector β Real-time COβ estimation from vehicle detection wiht TFlite phone inference
- Educational Website β Headless LMS for managing course content and payment gateways (CSYA)
- RL-Maze β Reinforcement Learning Agent for simulating maze
- SafeSentry β React Native app with real-time firestore, geolocation tracking, & push notifs (TechXcelerate'23 Winner)
- Risk-Sensitive Forward Modeling for Delayed Teleoperation Using Cumulative Prospect Theory - CPT-based VAE model blending human risk perception for teleoperation safety under communication delay (inprog)
- Google Gemini SDK β Added asynchronous functions & library optimizations
- Intel Retail AI Suite β LiDAR-based theft-detection module in pilot tests.



