Data infrastructure and pipeline
Create, build, and maintain the infrastructure required for optimal extraction, transformation, and loading of data from a wide variety of sources.
Deliver high-quality, production-ready data pipelines that bring and cleanse data from source systems to support AFC model build.
Implement processes/systems to monitor data quality, and drive optimization, testing and tooling to improve data quality.
Support model development and deployment
Liaise closely with relevant stakeholders to identify and assess suitability of data for AFC models. Liaise with Business Analyst and ensure assembled data sets used for model build meet business requirements.
Support Data Scientist(s) in developing model narratives by providing inputs from a data perspective; and in ongoing testing of models/outputs during development, prior to more formal model validation by an independent team;
Create a model deployment pipeline to automate deployment of models in UOBV’s environments/systems, and work closely with Data Scientist(s) in the Modelling team and other stakeholders (e.g., Group Technology and Operations) to ensure models are production ready.
Ensure the seamless deployment of new AFC analytics solutions and models without breaking anything or creating unintended effects in the production pipeline.
Enhancement, Support and Team Contributions
Identify, design, and implement enhancements for internal process related to data (e.g., optimizing data delivery, re-designing infrastructure for greater scalability) to improve data reliability, efficiency, and quality.
Performs data analysis required to troubleshoot data related issues and support the resolution of raised data issues.
Support the validation team lead in defining and maintaining minimum standards of model performance, applicable at the time of model development and upheld via subsequent validation exercises
