1. Advanced Analytics Product Development
Design and build machine learning models aligned to core personal banking priorities
Identify commercially viable use cases in collaboration with product marketing and business stakeholders
Drive the development of analytics products that are scalable measurable and operationally robust
2. Model Development and Lifecycle Management
Build test and deploy machine learning models into production environments
Ensure models are aligned with Model Risk Management standards and delivery governance
Monitor model performance and lead retraining or recalibration processes as needed
3. MLOps and Operationalisation
Implement production-ready model pipelines using CI/CD tooling and automated monitoring
Ensure continuity of performance and data integrity throughout the lifecycle
4. Feature Engineering and Data Exploration
Lead the extraction and transformation of raw data into high-quality features
Conduct deep EDA to identify trends correlations and value-driving insights
Understand and navigate complex banking datasets including transactional behavioural and product data
5. Business Engagement and Communication
Present modelling outcomes and insights to senior non-technical stakeholders with clarity and precision
Translate business opportunities into concrete data science initiatives
Provide clear recommendations and options based on data-driven insights
6. Innovation and Delivery Focus
Develop and prototype new modelling techniques and innovative data products with a commercial lens
Prioritise delivery and measurable value over theoretical perfection
Contribute to the development of reusable frameworks and accelerators to optimise delivery methodologies for data science teams
Qualifications :
Required Experience and Skills:
5 years of applied data science experience in a banking environment
Proven track record of deploying production-grade models with ongoing performance management
Strong hands-on skills in SQL Python and ML libraries (e.g. scikit-learn XGBoost)
Demonstrated experience in feature engineering and large-scale data handling
Familiarity with MLOps pipelines and tooling for monitoring and automation
Strong commercial acumen and ability to scope and deliver high-impact use cases
Excellent presentation communication and stakeholder engagement skills
Deep understanding of model governance standards and regulatory expectations
Preferred Qualifications:
Experience with platforms such as Dataiku and Databricks is a significant bonus
Strong Retail banking domain knowledge
Proven experience with statistical modelling mastery
Bachelors or Masters degree in a quantitative field (e.g. Computer Science Statistics Engineering)
Experience working in cloud environments (Azure AWS or GCP)
Remote Work :
No
Employment Type :
Full-time
