Assistant Vice President.Retail Risk Analytics-Risk Management

Overview

This role is responsible for the development, implementation, and ongoing maintenance of credit risk models and scorecards for the retail portfolio lifecycle, supporting underwriting and portfolio management decisions. Responsibilities include model design, performance monitoring, validation, regulatory reporting support, and governance, with strong collaboration across policy, finance, IT/data, internal audit, and compliance.

Responsibilities

• Develop, implement, and maintain credit risk models and scorecards across the retail portfolio lifecycle (acquisition, behavioral, collections), including PD, LGD, and EAD.
• Lead the design and enhancement of credit risk modelling frameworks using appropriate statistical/analytical techniques to support underwriting and portfolio management.
• Monitor, document, and communicate model performance, assumptions, and limitations to stakeholders to ensure transparency and model interpretability.
• Perform model monitoring, backtesting, and periodic recalibration to keep models accurate, stable, and compliant.
• Recommend model redevelopment or enhancement based on portfolio trends, data drift, and emerging risk patterns.
• Support Basel regulatory reporting, including RWA estimation and model-related submissions aligned with internal and regulatory requirements.
• Lead/support IFRS 9 ECL modelling, including staging, macroeconomic overlays, scenario-based expected credit loss estimation, stress testing, and climate risk.
• Deploy credit risk models into production systems/rating platforms, working with IT and data teams to ensure data integrity and system robustness.
• Support the design and implementation of credit risk strategies and decision rules (e.g., cut-offs, risk segmentation, line management) aligned with model outputs.
• Perform and oversee model validation and testing activities (functional, statistical, and regulatory) prior to deployment.
• Establish robust model governance practices, including documentation and audit trails, in line with regulatory standards.
• Identify opportunities to enhance credit risk models using advanced analytics and machine learning where appropriate and justifiable.
• Establish MLOps standards for model deployment, monitoring, versioning, and performance tracking in production environments.
• Develop data-driven insights to monitor portfolio quality, risk trends, and early warning indicators.
• Collaborate with policy, finance, and business teams to support portfolio optimization, provisioning, and capital management decisions.
• Ensure timely communication of model performance, validation findings, and risk insights to senior management and committees.
• Mentor junior analysts and contribute to building a technically proficient credit risk modelling team.
• Perform other duties as assigned.

Requirements

• 10–12+ years of experience in credit risk modelling within retail banking or financial services.
• Strong analytical and structured problem-solving skills in credit risk modelling and portfolio analytics.
• Deep understanding of credit scorecard development, validation techniques, and model risk management practices.
• Strong end-to-end experience across model development, validation, implementation, and performance monitoring.
• Ability to diagnose model performance issues (e.g., drift, instability, segmentation breakdown) and recommend corrective actions.
• Technical proficiency in SAS, SQL, and Python/R, particularly in handling large datasets.
• Demonstrated stakeholder management skills and ability to communicate complex modelling concepts clearly.
• Ability to translate quantitative outputs into practical business and risk decisions.

Preferred Qualifications

• Proven track record of building, deploying, and maintaining production ML models with real-time or near-real-time decisioning systems.
• Experience with credit risk strategy development and portfolio analytics.
• Familiarity with decision systems/rule engines (advantage).
• Professional certifications such as FRM or CFA (highly desirable/strong plus).
• Experience with MLOps tooling (e.g., MLflow or similar platforms) (highly desirable).

Education

• Degree in quantitative disciplines (Statistics, Mathematics, Actuarial Science, or Economics).

Compensation & Benefits

• Not specified in the provided description.

Location

• MENA (Middle East and North Africa).