Data analyst intern

About the Role

We are looking for a curious and technically inclined intern to help build automated data collection and document-processing pipelines for an AI-powered customs and trade intelligence platform. The project involves collecting regulatory information from official sources, processing PDFs and scanned documents using OCR, extracting structured data, and organizing it into reliable datasets that can support customs compliance and AI-based analysis. We value practical problem-solving, ownership, and the ability to use AI coding tools effectively while understanding, testing, and improving the code they generate.

Key Responsibilities

• Build and maintain web-scraping pipelines to collect information from official websites and public regulatory sources, including DGFT, CBIC, e-Gazette publications, and Free Trade Agreement documents.
• Use Python and relevant libraries to automate data extraction, cleaning, transformation, and storage.
• Download, process, and extract information from PDFs, including scanned documents requiring OCR.
• Extract structured information such as notification numbers, dates, HS codes, duty rates, exemptions, and regulatory conditions where available.
• Use AI coding tools to accelerate development, debug errors, and improve existing scripts.
• Validate extracted information against original documents and handle missing, inconsistent, or duplicate records.
• Organize data into structured formats such as CSV, JSON, Excel, and relational databases.
• Implement error handling, logging, retries, and automated checks to make pipelines reliable.
• Document code, workflows, and data sources for future development.

Requirements & Tech Stack

• Basic to intermediate Python programming.
• Practical experience with AI-assisted development tools such as Cursor, Claude, ChatGPT, GitHub Copilot, or similar tools.
• Ability to understand, debug, modify, test, and improve AI-generated code.
• Basic understanding of web scraping, HTML, APIs, JSON, and HTTP requests.
• Familiarity with Python libraries such as Requests, BeautifulSoup, Pandas, and Selenium or Playwright.
• Basic knowledge of PDF processing and OCR tools, or a strong willingness to learn them.
• Familiarity with Excel, CSV files, data cleaning, and structured data management.
• Strong problem-solving skills, attention to detail, and willingness to learn independently.

Good to Have

• Experience with Scrapy, PyMuPDF, Tesseract OCR, OCRmyPDF, or PDF table extraction.
• Basic SQL and PostgreSQL knowledge.
• Experience working with large datasets or automated data pipelines.
• Interest in AI applications, document intelligence, customs regulations, international trade, or regulatory technology.

What We’re Looking For

Someone who can go beyond simply generating code with AI. We want a candidate who understands the code they work with, can troubleshoot problems independently, validates extracted data for accuracy, and takes ownership of building reliable data pipelines. You do not need prior expertise in customs regulations. However, curiosity, technical initiative, and a willingness to work with complex regulatory documents are essential.