Credit Risk Modeler

Potential candidates should have knowledge in general math modeling, Machine Learning (ML) and related Operations Research (OR) and simulation techniques. Candidates should have hands-on experience in developing quantitative models. They should possess the ability to translate a business problem into an analytical problem, recommend, implement and validate quantitative models, and generate/deliver insights to stakeholders. Preference would be given to candidates that are intellectually curious, innovative thinkers, and have demonstrated ability to solve problems independently.
Responsibilities
Roles & Responsibilities
Support credit risk analytics activities across model development, independent validation, monitoring, and business reporting.
Conduct data extraction, reconciliation, quality checks, and analytical review using tools such as SQL, SAS, Python, Excel, and PowerPoint.
Translate analytical findings into clear insights and communicate results to model development, validation, business, and risk stakeholders.
Maintain clear documentation of analysis, validation observations, reporting logic, assumptions, and key findings.
Assist in the development and enhancement of IFRS 9 models, including PD, LGD, EAD, expected credit loss, and related risk estimation frameworks.
Perform independent validation activities by reviewing model methodology, assumptions, input data, outputs, performance, and documentation.
Analyze portfolio trends, credit risk drivers, delinquency patterns, default behavior, and model performance indicators to support risk decision-making.
Execute recurring business reports, dashboards, and management information packs accurately and within agreed timelines.
Qualifications
Qualifications
- Masters in Mathematics/Statistics/Economics/Engineering or any other related discipline or a track record of performance that demonstrate this ability
- Good exposure to ML techniques such as Clustering/classification/decision trees, Random forests and related algorithms
- Excellent problem solving, communication, and data presentation skills
Skills/Knowledge required
Masters in Finance, Financial Engineering, Analytics or Mathematics, Computer Science, Statistics, Industrial Engineering, Operations research, or related field.
Good understanding of Probability of Default (PD), LGD and EAD modeling technique.
Very good understanding of Predictive modeling techniques and their application.
Statistics and machine learning techniques.
Conducted and applied statistical methodologies including linear regression, logistic regression, ANOVA/ANCOVA, CHAID/CART, cluster analysis
Team player and collaboration skills.
Programming skills in R, SAS, and PYTHON.
Fluency with Excel, PowerPoint and Word
Strong written and oral presentation / communication skills – must have the ability to convey complex information simply and clearly
Experience with developing and implementing cloud based analytical solutions in GCP or similar set up.
Experience (Good to have):
3 - 5 Years exposure in Banking & Financial Services industry
Candidate should have worked in Credit Analytics (Mandatory) and preferably in Financial Analytics, Retail bank, Mortgage, Lending / liability product
Risk Analytics, Credit Risk Scorecard Development, Model Validation, IFRS 9 Validations, Credit Loss Forecasting
You'll be redirected to
the company's application page