You will be part of the Real World Data Science (RWDS) team and will be located in Basel. As part of the wider Data Science and Analytics department in the Late Stage Development unit of Roche’s Pharma division, we provide expertise in the conceptualisation, design, conduct and interpretation of RWD studies to help the development of and access to Roche’s medicines. 

In this position, you will:

• Explore existing AI-driven cardiovascular risk scores using real-world data to identify the impact of dynamic biomarker changes on risk estimation and treatment efficacy
• Develop and validate a machine learning algorithm to improve cardiovascular risk prediction based on lab-measured biomarker changes over time (e.g., NT-proBNP, hsCRP, lipids)
• Collaborate with experts in the Cardiovascular and Metabolic area to combine data science with clinical insights and prioritize key biomarkers for enhanced risk prediction
• Document and share your findings and recommendations to influence future cardiovascular research and trial designs
• Work with large-scale datasets and AI/ML techniques, gaining valuable professional experience and contributing to cutting-edge advancements at Roche.

You have earned an M.Sc. within the past 12 months prior to the start date, or you are currently enrolled in a Master's degree or PhD program in data science, epidemiology, statistics, or a similar quantitative discipline, and have very good knowledge of programming in R or Python.
Successful applicants will demonstrate a keen interest to learn about new data, tools and methods, to experiment, and to complete the internship project within the allocated time. Prior experience and/or a keen interest in the specific project areas are a plus.
 

Moreover, you are:

• Experienced or have a strong willingness to learn both analysis of large claims or electronic medical records data and report/publication writing
• A person who works systematically and precisely and brings a high level of initiative as well as a dedicated attitude
• A proactive and transparent team worker
• Proficient in English
• Experienced with machine learning for prognostic modelling (ideally on time series data) and/or familiarity with cardiovascular risk scores and biomarkers (e.g., NT-proBNP, hsCRP, cholesterol) is a plus.