AI/ML Developer | Agentic Systems | RAG Pipelines
B.S. AI & Data Science — IIT Guwahati
I'm an AI/ML Developer passionate about building reliable and practical LLM systems. My focus is on moving beyond basic prompting by integrating structured logic, retrieval-augmented generation (RAG), and multi-agent coordination to create robust applications.
- 🔭 Currently Building: RxGuard — a local AI assistant exploring safer medication analysis workflows.
- 🧠 Interests: Agentic architectures, hallucination mitigation, and evaluation frameworks.
- 🤝 Looking For: AI/ML roles, research collaborations, and opportunities to contribute to experienced engineering teams.
- 📍 Location: India
🚀 Featured Project: RxGuard
A local clinical decision-support assistant designed to improve reliability in LLM-assisted medication analysis.
- Focus: Working to reduce LLM hallucinations in sensitive contexts by implementing structured verification stages.
- Approach: Utilizes a graph-structured multi-node workflow with typed state transitions for more predictable execution.
- Stack:
LangGraph•Ollama•FAISS•Pydantic•Streamlit
Core Areas: LangChain • LangGraph • RAG • Agentic Workflows • Vector DBs
| Project | Description | Stack |
|---|---|---|
| LangGraph Blog Agent | Multi-agent content generator exploring parallel drafting | LangGraph, Groq, Tavily |
| Video-RAG Analyst | Query video transcripts using semantic search | LangChain, FAISS, HF |
| Sentiment Classifier | Improved noisy-text accuracy from 65% to 86% | LightGBM, sklearn |