Data & System Intern

Be a part of a revolutionary change Times are changing at PMI. We’ve chosen to do something big. The world expects us to act responsibly. And we are doing just that by transforming our business and building our future on one clear purpose – to deliver a smoke-free future. This transformation will revolutionise every area of our business. The products we sell. Where we sell them. How they’re manufactured and delivered. The way we talk to our customers and engage with society. It’s the perfect setting place to start your career. As you take your first steps, you’ll have the backing of a multinational business combined with the freedom of a start-up. You’ll bring a positive mindset and fresh perspective to projects that can make a huge difference to so many. About the team Part of Preclinical Sciences & Toxicology group, the Data & Systems team ensures that the scientists are equipped with the right data and software to perform their jobs. The keys systems managed by the team are a Laboratory Information Management System and the central scientific data repository. Who we’re looking for We are seeking a dedicated and enthusiastic intern who is currently pursuing a Master’s or Bachelor’s degree in Data Science/Engineering, Bioinformatics, or Biology. The ideal candidate should have: • Availability from mid-July to February • Programming experience in Python. • Knowledge or a strong desire to learn natural language processing, scripting with Large Language Models (e.g., langchain), and parsing of documents (e.g., PDF, Word) using Python. • Knowledge of biology and in vitro toxicology will be an asset but is not mandatory. Roles & Objectives The objective of the internship is to extract historical scientific data stored in around 300 study reports and consolidate the data in a predefined structured table. This will enable scientists to leverage historical data to make better and faster decisions. The intern will: • Have access to the PMI Data Science platform as well as the Preclinical Sciences & Toxicology High Performance Computing environments. • Collaborate with the Enterprise Analytics and Data team. • Gather the study reports from the current storage systems in a location suitable for processing them (e.g., AWS S3 bucket). • Leverage the work already performed by the Enterprise Analytics and Data team to explore the best strategy and tools for data extraction. The technologies can include for instance document parsing libraries, natural language processing, and Large Language Models. • Develop a script to extract the data from the report and consolidate it in a predefined table format. • Measure the level of confidence and percentage of completion achieved by the automated data extraction. • Ultimately, define and execute the data extraction on the documents and ensure the verification of the data to achieve full confidence in the extracted data. • If time allows, apply the same approach to another set of more exploratory study reports. This is an excellent opportunity for students to gain hands-on experience and contribute to a meaningful project. We look forward to welcoming our new intern to the team! What we offer Our success depends on our talented employees who come to work here every single day with a sense of purpose and an appetite for progress. Join PMI and you too can: • Seize the freedom to shape your future and ours. We’ll empower you to take risks, experiment and explore. • Be part of an inclusive, diverse culture, where everyone’s contribution is respected; collaborate with some of the world’s best people and feel like you belong. • Pursue your ambitions and develop your skills with a global business –our staggering size and scale provides endless opportunities to progress. • Take pride in delivering our promise to society: to deliver a smoke-free future. PMI is an Equal Opportunity Employer.