Data Scientist

Overview

Data Scientist for Shell’s Digital Process Twin (DPT) portfolio within the Commercial Data Science team, using process mining and AI/ML to improve business-process performance.

What you'll do

• Develop and implement machine learning and optimization models using process event data.
• Use process-mining and AI/ML techniques to discover process patterns and identify improvement opportunities.
• Build and maintain process data models by integrating and transforming enterprise data into analysis-ready pipelines.
• Embed models into Shell’s process-mining platform for scalable, real-time analytics through collaboration with engineering teams.
• Develop algorithms for anomaly detection, forecasting, and prescriptive optimization using process-mining insights with AI/ML.
• Implement MLOps/DevOps workflows for model lifecycle management using GitHub and CI/CD pipelines.

What you'll need

• 6–8 years of experience in data science, including hands-on AI/ML or optimization models.
• At least 2 years working with process event or behavioral data.
• Bachelor’s or Master’s degree in a relevant quantitative field (Computer Science, Data Science, Engineering, Mathematics, or related).
• Proficiency in Python and SQL and data-modeling techniques for event data.
• Experience with process data model design, development, and deployment using reusable schemas and pipelines.
• Experience integrating ML models with process-mining platforms such as Celonis EMS or open-source frameworks (PM4Py, ProM).
• Familiarity with Agile development plus MLOps/DevOps practices for automation, testing, and deployment.