S&T Data Solidation & AI Analysis - Intern

Imerys • Johns Creek, GA

9d

About The Position

Imerys is the world’s leading supplier of mineral-based specialty solutions for the industry with €3.4 billion in revenue and 12,300 employees in 40 countries in 2025. The Group offers high value-added and functional solutions to a wide range of industries and fast-growing markets such as solutions for the energy transition and sustainable construction, as well as natural solutions for consumer goods. Imerys draws on its understanding of applications, technological knowledge, and expertise in material science to deliver solutions which contribute essential properties to customers’ products and their performance. As part of its commitment to responsible development, Imerys promotes environmentally friendly products and processes in addition to supporting its customers in their decarbonization efforts. Imerys is listed on Euronext Paris (France) with the ticker symbol NK.PA. The PositionS&T Data Solidation & AI Analysis - Intern Job Summary Project Scope: The intern will play a critical role in modernizing the Science & Technology data architecture by leading the development of an automated ETL (Extract, Transform, Load) pipeline. This project focuses on transitioning scattered historical analytical data (e.g., Mineral analyticals, Application, SEM/EDS particle data) into an AI-ready master database using Python and Large Language Models (such as NotebookLM). The intern will apply data engineering best practices to ensure robust data provenance, standardization, and retrieval during the development phase. Project Description: This project centers on data engineering and AI-driven analysis of historical mineral research data. Utilizing Python libraries (pandas, openpyxl), the intern will design and execute scripts to extract, clean, and merge complex Excel workbooks into consolidated formats (Excel and Markdown). A clear and concise report and presentation should be produced by the intern describing the data architecture, the AI prompting methodologies utilized, and the actionable insights discovered from the historical data. Data Engineering: Build and optimize Python scripts to automate data extraction, transformation, and formatting across multiple network directories and cloud drives. AI Integration: Utilize Retrieval-Augmented Generation (RAG) tools like NotebookLM to analyze compiled datasets, audit historical reports against Imerys SOPs, and identify multi-variable trends. Quality Assurance: Implement robust code safeguards (e.g., handling missing data, creating tracking columns for Source Files/Tabs) to guarantee data traceability and integrity. Data Synthesis: Analyze combined metadata to spot geographical or locational trends, profile edge-cases, and compile findings into technical reports. Project Learning Objectives: Data Architecture & ETL: Gain hands-on experience designing and deploying automated Python pipelines to handle, clean, and standardize real-world corporate data. AI Tool Application: Develop practical expertise in formatting datasets for Large Language Models and engineering advanced prompts to conduct qualitative data analysis and compliance auditing. Technical Proficiency: Develop advanced proficiency in Python data manipulation (pandas), Markdown formatting, and version control within process engineering contexts. Cross-Functional Communication: Master the ability to translate complex data architectures into clear visual presentations and strengthen communication by building professional relationships with teams across S&T and engineering.

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.

What This Job Offers

• Job Type: Full-time
• Career Level: Intern
• Education Level: No Education Listed
• Number of Employees: 5,001-10,000 employees