Senior Data Scientist
We are building an enterprise-grade AI platform to enable secure, scalable and production-ready use of Generative AI, ML and advanced analytics across the Customs Declaration Service.
The Data Scientist will work across large-scale data, machine learning, graph analytics and statistical modelling to identify complex relationships, patterns and risks within enterprise datasets.
This role combines data science, engineering and advanced analytics to develop models and insights that can support fraud detection and data-driven decision making.
Location: Anywhere in the UK, with the option to attend the office when required.
Key Skills
- Python, PySpark and SQL
- AWS and cloud-based data engineering
- ETL pipeline development and data processing
- Graph analytics and graph processing
- GraphX and Pregel or equivalent graph processing technologies
- Machine learning and statistical modelling
- Fraud detection and network analysis
- Data analysis, analytics and visualisation
- Artificial Intelligence and statistical programming
- Strong mathematical and numerical analysis skills
- Data manipulation and feature engineering
- Technology change management
Key Responsibilities
- Develop ETL pipelines to process large-scale tax and enterprise data using Python, Spark, SQL and AWS
- Build and analyse large-scale graphs linking hundreds of millions of entities to identify fraudulent patterns
- Develop features to analyse relationships between entities and fraud risk
- Implement community detection algorithms to uncover fraudulent networks
- Train and develop machine learning models to detect fraud, including fraud within support schemes
- Apply statistical modelling and analytical techniques to complex datasets
- Develop visualisations to present graph and analytical data to business users
- Work across data engineering, analytics and AI capabilities to turn complex datasets into actionable insights
- Contribute to scalable, production-ready data science and AI capabilities within an enterprise environment