Credit and Risk Manager

Role Overview

You will own the end-to-end credit risk lifecycle, using AI-driven models and predictive analytics to refine lending strategies and reduce default rates. Day to day, this means designing, validating, and deploying machine-learning-based scoring systems while collaborating with data engineers, product teams, and business stakeholders to align risk appetite with commercial growth. Your work directly enables faster, more accurate loan decisions that balance profitability with prudent risk exposure.

Key Responsibilities

• Develop and maintain credit risk models (e.g., probability of default, loss given default) using machine learning techniques such as gradient boosting, neural networks, or ensemble methods.
• Automate credit assessment workflows by integrating AI/ML outputs into underwriting decision engines and real-time scoring dashboards.
• Analyse large datasets from internal and external sources (credit bureaus, transaction history, behavioral data) to identify emerging risk patterns and refine lending criteria.
• Lead portfolio monitoring and stress testing – produce monthly risk reports, flag deterioration in segments, and recommend proactive adjustments to credit policies.
• Collaborate with data science teams to feature-engineer new predictive variables and validate model performance (AUC, KS, Gini, lift charts).
• Present risk insights and model recommendations to credit committee and senior management, translating technical outputs into actionable business language.
• Ensure all credit risk models comply with regulatory standards and internal governance frameworks, including model documentation, validation, and audit trails.
• Mentor junior analysts on statistical methods, model interpretation, and best practices in credit risk analytics.

Requirements & Qualifications

• Bachelor’s degree in Finance, Economics, Statistics, Data Science, or a closely related quantitative field.
• 5+ years of progressive experience in credit risk management within a bank, fintech, or lending platform.
• Proven hands-on experience with AI/ML tools (e.g., Python scikit-learn, XGBoost, TensorFlow, or similar) and data analytics libraries (pandas, NumPy).
• Strong background in statistical modeling (logistic regression, decision trees, random forests) and model validation techniques.
• Advanced proficiency in SQL for complex data extraction and manipulation across large relational databases.
• Excellent analytical and decision-making skills – ability to weigh trade-offs between risk and revenue in a fast-paced environment.
• Familiarity with credit risk regulations (e.g., Basel, IFRS 9, CECL) and internal policy frameworks.
• Experience presenting quantitative findings to non-technical stakeholders and influencing strategic lending decisions.