Data Scientist – Personalization

About the role

We are looking for a Data Scientist specialized in personalization to turn large structured and unstructured data sets into actionable insights for personal and private banking clients. You will work closely with client, data, and technology teams to design and deliver contextually relevant conversations that drive acquisition, retention, and cross‑sell outcomes.

Key responsibilities

• Apply data mining, statistical analysis, and machine learning techniques to large data sets.
• Model business problems and discover insights through visualization and algorithmic approaches.
• Co‑create and enhance a client conversation portal that enables bankers to have meaningful, personalized interactions.
• Build, maintain, and improve statistically robust campaign models for acquisition, retention, right‑sell, and cross‑sell interventions.
• Design, develop, and deploy scalable data pipelines and ML solutions on cloud platforms such as Azure and AWS.
• Operationalise models using MLOps practices, including deployment, monitoring, versioning, and automated retraining.
• Apply advanced AI techniques—including NLP, recommender systems, and Generative AI—to boost personalization and customer engagement.
• Implement experimentation frameworks (A/B testing, uplift modelling, causal inference) to measure and optimise outcomes.
• Ensure compliance with data governance, model risk management, and responsible AI principles.

Required profile

• First degree in Mathematical Sciences, Information Technology or a related field; Master’s degree in Business or Commerce is a plus.
• 5–7 years of proven experience in quantitative analytics, modelling, and delivering customer‑focused outcomes.
• Demonstrated track record in translating data into actionable insights for banking or financial services.
• Experience working with unstructured data such as streams or images.

Required skills

• Data mining and statistical analysis
• Machine learning and advanced AI (NLP, recommender systems, Generative AI)
• Cloud platforms: Azure, AWS
• MLOps practices (deployment, monitoring, versioning, automated retraining)
• Data pipeline design and implementation
• Experimentation frameworks: A/B testing, uplift modelling, causal inference