Data Scientist III / IV

We are seeking a highly skilled and innovative Data Scientist to strengthen our credit risk modelling team. As a Senior Data Scientist, you will be a technical leader owning high-impact machine learning solutions across the entire borrower journey. You will partner with business leaders to drive growth, manage risk, and optimise operations.
Responsibilities:
End-to-End Borrower Lifecycle Modelling: Develop and deploy advanced machine learning solutions across the entire lending value chain, optimising customer acquisition (propensity-to-borrow, uplift models, CAC/ROAS), strengthening credit risk underwriting (PD, LGD, risk-based pricing), and driving intelligent collections strategies (propensity-to-pay, dynamic recovery interventions).
End-to-End Execution: Own the complete machine learning lifecycle, from translating ambiguous business requirements into mathematical frameworks to data pipeline creation, model training, and production deployment.
Cross-Functional Leadership and Mentorship: Act as the strategic bridge between technical teams and business stakeholders (Risk, Growth, Ops). Mentor junior Data Scientists, conduct rigorous code reviews, and elevate the team's technical standards.
Requirements:
We are looking for a seasoned practitioner with a deep understanding of algorithmic development and a proven track record of solving complex problems within the financial services ecosystem.
Experience: 5-8+ years of hands-on industry experience in Data Science, with a core focus on FinTech, consumer lending, or banking.
Domain Expertise: Deep understanding of lending economics and the regulatory landscape. Proven experience building models for at least two of the following: marketing/growth, credit risk scorecards, or debt recovery/collections.
Programming Mastery: Expert-level proficiency in Python (Pandas, Scikit-learn, NumPy) and SQL for complex data manipulation and feature engineering on large-scale datasets.
Machine Learning and Statistics: Deep practical knowledge of ensemble methods (e. g., XGBoost, LightGBM, Random Forests) and foundational statistical models (Logistic Regression, Generalised Linear Models).
Familiarity with survival analysis, causal inference, and experimental design (A/B testing).
Big Data and Cloud Infrastructure: Experience extracting and processing large datasets using distributed computing frameworks (e. g., PySpark).
Proficiency within modern cloud ecosystems (AWS, GCP, or Azure).
MLOps and Deployment: Solid track record of bringing models to production. Familiarity with version control (Git), orchestration tools (Airflow), and ML lifecycle management (MLflow, CI/CD pipelines, model monitoring).

Experience
5-8 yrs