Data Scientist

We are seeking an experienced Data Scientist to join its Consumer CVM and Loyalty team. The successful candidate will be responsible for developing and enhancing advanced machine learning models, personalised recommendation engines and predictive analytics solutions to drive customer engagement, product adoption and commercial value. The role involves working with large-scale datasets, developing customer propensity and product recommendation models, and implementing adaptive, data-driven AI and machine learning solutions. Strong hands-on experience in Python, SQL, Spark/Databricks and MLOps is essential, together with the ability to deploy and monitor machine learning models in production environments. The successful candidate will also provide technical leadership, mentor junior data scientists and collaborate with cross-functional teams to deliver measurable business outcomes.

• Build and enhance personalised recommendation models for customer-facing product platforms.

• Develop customer propensity, product selection, ranking, pricing and affordability optimisation models.

• Evolve existing scoring approaches towards adaptive, data-driven machine learning and AI decision-making.

• Develop customer-level features using usage, spend, recharge, purchase, engagement and response behaviour.

• Build, train, validate and optimise predictive and recommendation models using appropriate statistical and machine learning techniques.

• Develop learning-to-rank, experimentation, uplift and adaptive-learning approaches where applicable.

• Design and implement control groups, champion/challenger tests and experimentation frameworks.

• Establish and monitor model performance metrics, including predictive accuracy, lift, calibration and commercial impact.

• Implement model explainability and interpretability within recommendation decision-making.

• Monitor model performance, feature drift and model degradation over time.

• Perform advanced data analysis, including cluster profiling, cohort analysis and penetration/lift analysis, using large datasets.

• Query, manipulate and analyse data using SQL (Hive/Trino) and Python (Pandas/PySpark).

• Generate actionable business insights and recommendations from analytical and model outputs.

• Lead complex analytical investigations and translate findings into measurable commercial decisions.

• Establish reusable analytical frameworks, curated features and data quality checks.

• Lead the transition of machine learning models from development into production environments.

• Implement MLOps best practices, including version control, experiment tracking, model registration, automated testing and CI/CD pipelines.

• Establish production-readiness criteria covering data quality, model validation, explainability, security, documentation and operational support.

• Monitor data drift, concept drift, model performance, service reliability and business outcomes.

• Maintain model lifecycle governance, technical documentation and audit evidence.

• Provide technical leadership, coaching and structured peer reviews to data scientists and cross-functional delivery teams.

• Mentor graduates and interns while supporting technical upskilling initiatives.

• Collaborate with data engineering, MLOps, BI, architecture, AI Ops and business stakeholders to ensure successful solution delivery.

• Minimum 3-year tertiary qualification in a STEM-related field, such as:

  • Computer Science

  • Engineering

  • Mathematics

  • Statistics

  • Data Science

  • Or a related quantitative discipline.

• Honours or Master's degree in Data Science, Statistics or a related field will be advantageous.

• 5–10 years of experience in Data Science or Advanced Analytics.

• Demonstrated experience in developing and deploying complex machine learning solutions into production.

• Hands-on MLOps experience is mandatory.

• Strong programming and query language skills:

  • Python (Pandas, PySpark).

  • SQL (Hive, Trino).

• Experience with big data and machine learning platforms, particularly Databricks and Spark.

• Strong knowledge of machine learning algorithms and techniques, including:

  • K-Means and Clustering.

  • XGBoost.

  • CatBoost.

  • LightGBM.

  • Classification and Regression.

  • Anomaly Detection.

• Hands-on experience with MLOps and DevOps tools, including:

  • MLflow.

  • CI/CD Pipelines.

  • Azure DevOps.

  • Model Monitoring and Drift Detection.

• Experience with Power BI and Databricks for data visualisation and reporting.

• Knowledge of model governance, explainability, risk controls, data quality and production monitoring.

• Experience with large-scale distributed data processing is highly advantageous.

•