AVP - Treasury Quantitative Analytics in London

We have an exciting opportunity for an AVP level candidate to join the newly created Treasury Quantitative analytics division of a leading universal banking client of ours. The role is primarily to design, develop, implement, and support mathematical, statistical, and machine learning models and analytics used in business decision-making. The role will be London based and offer a hybrid working pattern to the successful applicant

Role Description

Design analytics and modelling solutions to complex business problems using domain expertise

Collaboration with technology to specify any dependencies required for analytical solutions, such as data, development environments and tools

Development of high performing, comprehensively documented analytics and modelling solutions, demonstrating their efficacy to business users and independent validation teams

Implementation of analytics and models in accurate, stable, well-tested software and work with technology to operationalise them

Provision of ongoing support for the continued effectiveness of analytics and modelling solutions to users

Demonstrate conformance to all the Bank’s Enterprise Risk Management Policies, particularly Model Risk Policy

Ensure all development activities are undertaken within the defined control environment

Role Requirements

Deep understanding of statistical and econometric modelling techniques – e.g. time series analysis, regression models and various estimation techniques

Excellent communication skills, including the ability to discuss technical matters with a non-technical audience as well as being proficient in python programming

Previous experience in modelling non-maturing deposits, mortgage prepayment or mortgage completion models

Strong experience in analysing large volumes of data including cleaning and subsequent pattern identification and clustering

Experience developing, implementing of models which utilise more complex Machine learning techniques

Python experience would be ideal, but not essential

#J-18808-Ljbffr