Senior Data Scientist - Fleet Solutions

Key Skills

Algorithms, Azure, Data science techniques, Databricks, Effective communication skills, Git, Machine learning techniques, Mathematics, Object-Oriented programming (OO languages), Optimization, Project management, PySpark, Python Programming, UML

Job Description

Are you a data scientist with strong programming skills and experience in Machine Learning solutions design and implementation? If you enjoy writing clean code, solving complex challenges, thinking at scale, and unlocking the value of data - read on.

Fleet Solutions in a nutshell is the Fleet Card Business. Shell Fleet Solutions is a global leader in business mobility (B2B segment), enabling business customers to decarbonize and providing them with integrated Shell and partner offerings. Using Fleet Card, Shell Fleet Solutions customers perform transactions related to fuel, electricity, and other service purchases on a daily basis. The card is accepted not only by the Shell stations but also by the numerous points of sales of our partners. On top of that, customers use Shell web resources (such as Shell Fleet Hub) to manage their cards and propositions.

As a data scientist with ML engineering specialization, you’re going to be responsible for:

• Developing advanced Data science solutions for problem statements in the area of Mobility and Fleet Solutions
• Designing and implementing modeling pipelines
• Aiding continuous integration and development by leveraging cloud services (Azure, Databricks).
• Setting up and demonstrating world-class standards and best practices in project execution and quality of delivery.
• Clearly communicating requirements, challenges, and solutions to other teams and stakeholders.

Requirements:

• Advanced Python programming and object-oriented software design.
• Knowledge of classical ML techniques (e.g. Classification algorithms, Clustering, Feature Reduction/engineering, Anomaly detection, Optimization models, Time Series Analysis/Forecasting), model evaluation, and the underlying mathematics.
• Knowledge of statistical methodology (e.g. Data Quality Analysis, Data identification, Hypothesis testing, Univariate / Multivariate Analysis, PCA, Factor Analysis).
• Experience using cloud services (Azure, Databricks preferred).
• Data storytelling.
• Project management.
• Git.

Nice to have:

• Experience with PySpark
• Algorithm optimization.
• Ability to read and design UML documentation.