Ishaan R.

Key Skills

Software

Roboflow

AWS SageMaker

Top Subject Matter

Healthcare Professional Segmentation and Engagement

Document Summarization and Analytics

Top Data Types

Text

Document

Image

Top Task Types

Classification

Text Summarization

Freelancer Overview

LLM-Powered Classification and RAG System (AI Software Engineer Intern). Brings 3+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include LangChain. Education includes Master of Science, Stony Brook University (2025). AI-training focus includes data types such as Text and Document and labeling workflows including Classification and Text Summarization.

Labeling Experience

LLM-Powered Classification and RAG System (AI Software Engineer Intern)

TextClassification

Designed and maintained a classification pipeline leveraging LLMs to segment and categorize text-based data on healthcare professionals. Developed a retrieval-augmented generation (RAG) system to generate personalized strategies from behavioral and sales data inputs. Oversaw end-to-end data pipeline deployment focused on model inference and categorization tasks. • Built text-engagement tiering for 50K+ healthcare professionals. • Used LLMs to automate labeling of engagement class for segmentation. • Integrated RAG for strategy generation using extracted text features. • Delivered real-time analytics and reporting using AWS tools.

2025 - 2025

Distributed RAG-Based Summarization Pipeline (Project)

DocumentText Summarization

Built and deployed a distributed summarization pipeline for real-time processing of diverse documents using RAG principles and LLM APIs. Oversaw intelligent chunking, context retrieval, and automated text summarization to enhance summary accuracy and label output quality. Incorporated interactive user evaluation and utility assessment in a live environment. • Processed and summarized 200+ documents per session with sub-3 second latency. • Used LangChain and Gemini API for text retrieval and summarization. • Supported summary label accuracy metrics with 80%+ user-rated reliability. • Enabled real-time labeling interface via Streamlit for document workflows.

Not specified

Education

Work History