Straive - Credit Risk Modeler

We are seeking a skilled Credit Risk Modeler to develop, validate, and maintain credit risk models that assess the creditworthiness of individuals and organizations. The role involves analyzing financial data, creating predictive models, and supporting the credit decision-making process to minimize potential losses and optimize risk-adjusted returns.

Key Responsibilities:

- Develop and implement credit risk models (e.g., Probability of Default (PD), Loss Given Default (LGD), Exposure at Default (EAD)) for retail and/or corporate portfolios.

- Conduct statistical analysis and predictive modeling using techniques such as logistic regression, decision trees, machine learning algorithms, and other quantitative methods.

- Collaborate with data teams to collect, clean, and preprocess data from multiple sources.

- Perform back-testing and validation of existing credit risk models to ensure accuracy and compliance with regulatory standards (e.g., Basel II/III).

- Prepare detailed documentation of modeling assumptions, methodology, and results.

- Provide insights and recommendations to credit risk managers and business stakeholders to improve risk management strategies.

- Stay up to date with industry best practices, regulatory requirements, and emerging trends in credit risk analytics.

- Participate in internal and external audits related to credit risk models.

- Support stress testing and scenario analysis for credit portfolios.

Qualifications:

- Strong experience 3+ years in credit risk modeling, preferably in banking or financial services.

- Bachelors or Masters degree in Finance, Economics, Statistics, Mathematics, Data Science, or related quantitative discipline.

- Proficiency in statistical and modeling tools such as SAS, R, Python, SQL, or equivalent.

- Good understanding of credit risk concepts and regulatory frameworks (Basel Accords, IFRS 9).

- Strong analytical skills with attention to detail and problem-solving ability.

- Excellent communication skills for explaining complex technical information to non-technical stakeholders.

- Experience with big data tools and machine learning techniques is a plus.

- Familiarity with credit risk software platforms is advantageous