Data Science Engineer

Description:

Join a pioneering and expanding team dedicated to excellence and innovation in the banking industry. We are seeking a dynamic Full Stack Data Science Engineer who is eager to learn, grow, and contribute to delivering market-leading solutions. This role focuses on the development and management of robust data science infrastructure and deployment pathways, essential for launching advanced pricing capabilities that drive significant business impact.

The ideal candidate will have a strong foundation in data infrastructure, with a willingness to expand their skills in predictive modelling through on-the-job training opportunities provided by the team. As the Pricing Portfolio Optimisation squad in CTB LOB, we are pioneers in leveraging big data to enhance the effectiveness of our customer pricing strategies. Our team works closely with stakeholders to communicate and implement pricing strategies.

The main role accountabilities and responsibilities will include:
 

• Develop and maintain technical architecture to ensure effective delivery of machine learning outcomes into existing business processes in Teradata.
• Lead the engagement with Group Data and Technology to operationalise the ML models on both local & Azure ML environments
• Lead the establishment and maintenance of a collaborative, reproducible data science environment that supports seamless handoffs among team members.
• Manage the full lifecycle of predictive model development and deployment, including model risk engagement.
• Utilise an agile approach for managing deliverables, employing tools such as Confluence for documentation and JIRA for project tracking.
• Collaborate closely with team members to refine and enhance predictive model performance iteratively after initial MVP launch.
• Effective delivery of machine learning outcomes integrated into existing business processes in Teradata.
• Successful deployment and maintenance of predictive models with documented risk engagement.
• Regular updates and tracked progress using Confluence and JIRA.
• Enhanced performance of predictive models post-MVP launch through iterative collaboration.