Pavan Indukuri

AI and Data Extern @ Extern

About

Early-career Software Engineer and Data Professional with hands-on experience building scalable backend services, cloud-based data pipelines, and AI-powered analytics applications. Proficient in Python, Java, SQL, AWS, and REST APIs, with experience in data cleaning, exploratory analysis, ETL development, and deploying production-ready systems. Strong foundation in machine learning workflows, data engineering principles, and full-stack development. Passionate about leveraging data to drive insights and build reliable, high-impact systems. Skilled in analyzing complex datasets, building innovative data solutions, and optimizing performance using tools like AWS, Tableau, and Python. Quick to adapt and eager to learn, with a proven track record of improving operational efficiency and enabling data-driven decision-making.

Country

United States

City

Atlanta

Industry

Information Technology & Services

Skill

R, Tableau, Scikit-Learn, pandas, Matplotlib, Big Data, Communication, Leadership, Network Troubleshooting, presenting data, Information Technology, Project Management, English, Business Operations, Research Skills, Problem Solving, MATLAB, SQL, Agile Methodologies, Analytical Skills

Experience

AI and Data Extern

Extern

2026-2 - Present · 8 mos

Southlake, TX

-Built modular, Al-powered pipelines to process 200+ page mortgage blob files-combining OCR (Tesseract, PaddleOCR), PDF parsing (PyMuPDF), and RAG techniques for intelligent data extraction, classification, and search. -Developed a document retrieval system using Llamalndex and Retrieval-Augmented Generation (RAG), optimized for multi-document mortgage blobs. Enhanced precision through chunk tuning, metadata filtering, and evaluation of open-source LLMs like Mistral and Phi-2. -Conducted end-to-end evaluation of the document intelligence system on 200+ page mortgage blobs-benchmarking OCR accuracy, RAG retrieval quality, and routing performance. Delivered a technical report outlining model trade-offs, optimization strategies, final deployment recommendations, and built a Ul for demo purposes.