Job Description

This is a unique opportunity to join the Financial Crime Data Science and Analytics area to lead the Strategic Transaction Monitoring Modelling team of Data Scientists and Engineers. Our purpose is to combat financial crime with data, analytics, and data science to protect our customers and to help people and businesses to prosper.

This critical role will report into the Head of Financial Crime Data Science and Analytics and work closely with the Transaction Monitoring (TM) L2 stakeholders while leading the team to deliver the agreed TM models to the strategic alert management systems.

The difference you’ll make.

• Interacting with internal stakeholders in financial crime control operations, regulatory governance, front office, calibration testers, model oversight and IT counterparts.
• Managing a high performing team of 5 data scientists, data analysts and data engineers.
• Managing the Transaction analytics and modelling lifecycles (agree on release scopes, manage analytical discovery work stack, improve scenario definitions and methodology where possible, manage model development with the team, manage model quality checks, manage sign offs and manage the implementation of the final models to the production environment).
• Setting the standards for code writing, testing and maintaining production-quality code, as well as for design, experiment, and evaluate algorithms, and models. Producing and managing appropriate model documentation is also an essential activity for this role.
• Improving methodologies, develop new data sources, testing model enhancements, and fine-tuning model parameters collaboratively with the team.

Required Knowledge, Skills, and Abilities

• Demonstrable knowledge of Transaction Monitoring Scenarios and/or proven track record of managing modelling lifecycles (scoping, analytics management, development management, control management, implementation to production environment) in regulatory projects from the financial industry.
• The successful team manager will be expected to have a good understanding of transaction monitoring methodologies, machine learning techniques in general and their applications in Financial Crime environment with have strong knowledge or previous hands-on experience of Python and/or R and SQL in a Big Data environment.
• Experience with distributed computational frameworks (Impala, Hive, Hadoop, Spark)
• Mastery of source control versioning (e.g.: GitLab) and unit-testing.
• Ability to explain complex topics and analysis to senior audiences.
• Knowledge of financial markets instruments and financial crime controls.