Senior, Data Scientist

• Skill/Requirements
• Minimum 5 years' experience building production data pipelines, including at least 2

years working with banking or payments transaction data.

• Advanced SQL expertise in at least two of the following databases: Oracle, Microsoft SQL

Server, and PostgreSQL. Experience with PL/SQL or T-SQL for stored procedure development
is required.

• Advanced Python skills, including pandas and the scientific computing stack, with

experience in data analysis, scheduled job development, and production file processing.
Experience with version control is expected as a standard working practice.

• Experience building, deploying, and monitoring machine learning models in production

environments using transaction, payments, or risk data. Able to explain model
performance issues, how they were identified, and the strategies used for retraining and
improvement. Experience in fraud detection and anomaly detection is highly preferred.

• Experience working with card scheme clearing and settlement files (Visa/Mastercard

formats) or core banking extracts, including identifying and resolving reconciliation
breaks.

• Demonstrated and verifiable experience in mentoring, coaching, and upskilling team

members.

• Desirable: Experience with JasperReports (.jrxml templates and server administration) or

a comparable Java-based reporting platform.

The Senior Data Scientist is responsible for designing and building the Bank’s data platform, reporting infrastructure, and advanced analytics solutions using transaction and operational data. The role develops data pipelines, automates reporting and exception controls, and deploys production-ready machine learning models that support operational efficiency, risk management, and business insights. The position also ensures sustainable capability through strong documentation, knowledge transfer, and hands-on mentoring of internal team members.

• Main Duties
• Design and build the reporting data layer: extracts from T24 (Oracle), the card

platform, settlement files and the channel databases (SQL Server / PostgreSQL) into a
masked, read-only reporting store.

• Develop and maintain daily exception controls, including failed transactions without

matching credits, authorization-versus-clearing differences, and settlement instructions
without confirmed transfers.

• Automate report production starting with the highest-effort manual reports, measuring

hours before and after.

• Design, deploy, and monitor the Bank’s first production-ready machine learning models

using transaction data, prioritizing anomaly detection on exception flows (failed
transactions and settlement differences), card fraud pattern analysis, and merchant and
customer analytics.

• Ensure all models operate within the Bank’s on-premises environment using Python and a

scikit-learn-class stack, with documented ownership, performance monitoring, and
retraining frameworks established before influencing business decisions.

• Guide the Data Engineer through hands-on collaboration on every pipeline and model in

line with the agreed roadmap, ensuring the Data Engineer can independently modify
pipelines, operate daily control, build one end to end pipeline independently and
retrain one model under supervision. These milestones form part of the role's objectives
and are reviewed quarterly.

• Mandate that all data pipelines and processes are documented clearly enough for a new

team member to run them without prior exposure.

• Perform other duties as assigned by the line manager.