Overview

Are you ready to unlock the potential of AI in document processing?

This externship will introduce students to AI-driven document processing for the mortgage industry, focusing on classifying document types and extracting useful data using AI models. Students will learn how to identify and classify different types of documents in a large "blob" file, extract meaningful data, and develop insights using AI models. Students will gain hands-on experience in natural language processing (NLP), computer vision, and data extraction from unstructured documents, equipping them with skills critical in industries like finance, real estate, and beyond.

Note: To remain eligible for the program, you must use your .edu email address associated with the community college you attend. Please ensure that you both verify your eligibility and schedule your interview using this email.
‍

During This Externship, You’ll Develop a Range of Skills, Including:

• Classify Mortgage Documents: Identify and categorize various document types using AI tools and techniques.
• Extract Valuable Data: Use Python and AI models to pull critical information from unstructured mortgage documents, such as salaries, dates, and account numbers.
• Analyze AI Model Performance: Evaluate open-source AI models for document classification and data extraction, identifying the best tools for real-world applications.‍
• Master NLP and Computer Vision: Gain hands-on experience with tools like DocLLM, LangChain, and LayoutLM to analyze and classify mortgage documents.‍
• Experiment with Open-Source Models: Benchmark the effectiveness of various AI models, comparing their strengths, limitations, and suitability for the mortgage industry.‍
• Deliver Actionable Insights: Develop and present recommendations for optimizing document processing workflows, leveraging the most effective AI tools.

‍

What’s Waiting for You:

• Hands-On Experience: Work on real-world projects, applying AI technologies to solve complex document processing challenges.
• A Competitive Edge: Enhance your resume with sought-after technical skills, preparing you for roles in AI development, data science, and beyond.
• Professional Network: Collaborate with industry professionals and peers, building connections that will support your career growth.
• Flexible Learning: Dedicate just 5-10 hours per week over 6 weeks, balancing the program with your existing commitments.

‍

This Could Be the Perfect Externship for You If:

• You are a student passionate about exploring the intersection of AI and document processing.
• You have an intermediate understanding of Python and familiarity with libraries like Pandas and NumPy.
• You have some exposure to machine learning concepts, particularly related to document classification or NLP.
• You have basic knowledge of AI models, with the ability to deploy and fine-tune models.
• You are familiar with Google Colab for code execution.
• You seek a flexible program that fits alongside your studies or work commitments.
• You are eager to build a portfolio of AI-driven projects that demonstrate your technical expertise.

Technologies Used

Throughout the externship, students will get hands-on experience with cutting-edge technologies, including:

• Python for data processing and AI development.
• Natural Language Processing (NLP) for analyzing and understanding text from documents.
• Document Processing libraries like PyPDF2, PyMuPDF, pdfplumber
• LlamaIndex to connect and manage large language models (LLMs) for querying documents.
• Document AI solutions like DocLLM for extracting structured information from PDFs and other document formats.
• Computer vision and generative AI models.
• Machine Learning models for document classification and feature extraction.
• Google Colab for model deployment and experimentation.

‍