Data Scientist

Job Description Data Science Engineer (Banking Domain)

Role Purpose

The Data Science Engineer will support the FinTech Hub in building next-generation data-driven capabilities, including predictive analytics, customer insights, risk modeling, fraud detection, and AI-assisted automation for core banking products. The role requires hands-on data engineering and applied data science experience within the banking industry, ensuring models and pipelines align with financial accuracy, compliance, and operational needs.

Key Responsibilities

Data Engineering & Pipeline Development

Build, optimize, and maintain scalable ETL/ELT data pipelines for structured and unstructured banking data.

Work with SQL Server, Sybase, and data lake architectures to prepare analytical datasets.

Develop feature stores, data marts, and high-quality datasets for ML and reporting.

Ensure data quality, consistency, lineage, and compliance with banking standards.

Applied Machine Learning & Predictive Modeling

Develop ML models for credit scoring, customer segmentation, churn prediction, fraud detection, transaction anomaly detection, and forecasting.

Handle the full ML lifecycle: preprocessing, training, validation, deployment, and monitoring.

Optimize models for performance, accuracy, and regulatory alignment.

Analytics & Business Insights

Build dashboards and analytical models for Finance, Risk, Branch Operations, and Product teams.

Translate raw data into actionable insights and KPIs.

Support experimentation, A/B testing, and hypothesis-driven analysis.

Collaboration & Banking Domain Alignment

Work with Product Owners, SMEs, and technical squads to embed analytics in core banking workflows.

Ensure compliance with audit, Risk, IFRS9, Basel, and AML requirements.

MLOps & Deployment

Deploy ML models using pipelines, Docker, and APIs.

Monitor model drift, data drift, and maintain long-term reliability.

Document model assumptions, behavior, and versioning.

Qualifications & Experience:

3+ years of experience as a Data Science Engineer, ML Engineer, or Data Engineer in a banking or financial institution.

Strong Python skills (Pandas, NumPy, Scikit-learn, PySpark preferred).

Strong SQL skills (SQL Server, Sybase, or other RDBMS).

Experience with ETL tools, data lakes, and distributed processing.

Proven experience building and deploying ML models in production environments.

Familiarity with credit scoring, IFRS9, risk modeling, or AML analytics is a strong plus.

Experience with BI tools such as Power BI or Tableau.