Open to opportunities

Netraj Patil

@netrajpatil

Message

Aspiring computer engineer building LLM workflows and autonomous agentic systems with production-ready Python.

India

Message

What I'm looking for

I’m looking for a role where I can build production-grade AI systems—especially LLM workflow optimization, evaluation, and agentic applications—while contributing strong backend engineering and scalable ML pipelines in a collaborative team.

I’m a Computer Engineering student with a strong interest in Artificial Intelligence—especially optimizing Large Language Model (LLM) workflows and building autonomous agentic systems. I enjoy turning research-grade ideas into practical, reliable software.

In my Data Science Intern role at Jio Platforms Limited (Reliance), I leveraged OCR technologies like docTR, Keras OCR, and pytesseract to build automated data extraction for complex document processing. I improved document comparison and validation using similarity score assessments, and supported real-time analysis by building a Flask RESTful API and data pipeline for production usage.

My projects reflect the same focus on LLM performance and system design. I built an LLM evaluation library (“LLM Jury”) for standardized scoring and benchmarking (including RAG and summarization), created “Glia,” a high-performance semantic caching library with a Watcher engine for automatic cache synchronization, and developed an autonomous AI assistant integrated with WhatsApp using LangChain/LangGraph, FastAPI, and external AI/search APIs.

Experience

Work history, roles, and key accomplishments

High-Performance Semantic Cache for RAG

Glia

Built a production-grade Python semantic caching library for LLM RAG that auto-synchronizes cache entries to prevent stale responses using CDC and polling.

RAG Python Threading ChromaDB Vector Similarity (KNN)Atomic Redis Pipelines SQL NoSQL Vector DB Integration

LLM Jury

Project

Developed a Python library to evaluate Large Language Model (LLM) performance with standardized scoring and benchmarking for tasks like RAG and summarization.

Data Science Intern

Jio Platforms Limited

Built automated OCR-based data extraction pipelines and improved document comparison accuracy using similarity scoring and layout-aware modeling. Developed production-oriented Flask APIs and machine learning datasets using Hugging Face.

Data Visualization Flask Python Data Pipelines REST APIs LayoutLMv3