Data Scientist

The Commercial Data Science (CDS) team partners with Shell's business units to deliver data-driven solutions through deep process understanding and technical excellence.

As a Data Scientist within the Digital Process Twin (DPT) portfolio, you will apply process mining, optimization, and AI/ML techniques to process-centric data to identify inefficiencies, predict process behavior, and optimize end-to-end business performance.

Responsibilities:

• Develop and implement machine learning and optimization models using process event data to predict, classify, and enhance business-process performance.
• Apply process-mining and AI/ML techniques to discover process patterns, identify root causes, and quantify improvement opportunities.
• Implement and maintain process data models , integrating and transforming data from enterprise systems into structured, analysis-ready pipelines for process-mining and machine-learning applications.
• Collaborate with senior data scientists, data engineers, and software developers to embed models into Shell's process-mining platform for scalable, real-time analytics.
• Develop algorithms that combine process-mining insights with AI/ML models for anomaly detection, forecasting, and prescriptive optimization.
• Implement MLOps and DevOps workflows for model lifecycle management, version control, deployment, and monitoring.
• Support the establishment of best practices in solution design, data quality, and delivery of scalable analytical products aligned with strategic business objectives.
• Contribute to research and innovation by evaluating emerging tools, algorithms, and open-source frameworks in process intelligence and digital twins.
• Ensure Responsible and Explainable AI (XAI) principles are embedded in all model development and deployment practices.

Requirements:

• 6–8 years of experience in data science, including hands-on development of AI/ML or optimization models and at least 2 years working with process event or behavioral data.
• Bachelor's or Master's degree in Computer Science, Data Science, Engineering, Mathematics, or a related quantitative field.
• Proven track record of building and deploying analytical solutions from concept to production.
• Demonstrated expertise in applying machine learning, statistical modeling, and process-mining algorithms to large, multi-source enterprise datasets.
• Strong programming proficiency in Python, SQL, and data-modeling techniques for event data.
• Experience in process data model design, development, and deployment, including creation of reusable data schemas and pipelines for process analytics.
• Experience integrating ML models with process-mining platforms.
• Familiarity with Agile development, MLOps, and DevOps practices for automation, testing, and deployment.
• Solid understanding of process data structures and their application in process-performance modeling.
• Exposure to cloud environments for data science workloads is desirable.
• Demonstrated commitment to technical rigor and model explainability through Responsible AI practices.

Benefits:

• Progress as a person while working on the energy transition.
• Continuously grow transferable skills.
• Work at the forefront of technology, trends, and practices.
• Collaborate with experienced colleagues.
• Achieve balance in a values-led culture.
• Join an organization working to become one of the most diverse and inclusive in the world.
• Grow through diverse career opportunities.
• Gain access to a wide range of training and development programs.