S&T Data Solidation & AI Analysis - Intern at Imerys · Johns…

Summary: Imerys is the world’s leading supplier of mineral-based specialty solutions for the industry. The intern will play a critical role in modernizing the Science & Technology data architecture by leading the development of an automated ETL pipeline and applying data engineering best practices to transition historical analytical data into an AI-ready master database. Responsibilities: - Build and optimize Python scripts to automate data extraction, transformation, and formatting across multiple network directories and cloud drives - Utilize Retrieval-Augmented Generation (RAG) tools like NotebookLM to analyze compiled datasets, audit historical reports against Imerys SOPs, and identify multi-variable trends - Implement robust code safeguards (e.g., handling missing data, creating tracking columns for Source Files/Tabs) to guarantee data traceability and integrity - Analyze combined metadata to spot geographical or locational trends, profile edge-cases, and compile findings into technical reports Required Qualifications: - Experience with Python programming, particularly with libraries such as pandas and openpyxl - Knowledge of data engineering best practices, including ETL (Extract, Transform, Load) processes - Ability to design and execute scripts for data extraction, cleaning, and merging - Familiarity with AI tools, specifically Retrieval-Augmented Generation (RAG) tools like NotebookLM - Strong analytical skills to identify trends and insights from complex datasets - Experience in producing clear and concise reports and presentations - Understanding of data quality assurance practices, including handling missing data and ensuring data integrity - Ability to communicate complex data architectures effectively to cross-functional teams Preferred Qualifications: - Experience with cloud storage solutions and network directories - Familiarity with Markdown formatting - Knowledge of version control systems - Experience in compliance auditing and qualitative data analysis Required Skills: Python, ETL Extract, ETL Transform, ETL Load, Data Engineering, Data Architecture, Large Language Models, Retrieval-Augmented Generation (RAG), pandas, openpyxl, Markdown, Version Control, Cross-Functional Communication