Quantitative Analyst at Capitec Bank

We're looking for a senior Machine Learning and Data Science Analyst to independently validate high‑impact models across credit risk, financial crime, and advanced analytics use cases.
This is a hands‑on technical role.


What You'll Be Doing
Leading the independent validation of machine learning models across:


Credit risk models
Propensity and behavioural models
Financial crime models (fraud and AML)
Applying advanced ML techniques, including:
Supervised learning (Random Forest, XGBoost, CatBoost, Neural Networks)
Unsupervised learning (clustering, isolation forests)
Managing model risk across the end‑to‑end model lifecycle, including:
Feature engineering and data preparation
Model training, evaluation, and selection
Production deployment and monitoring
Building and reviewing models in Python‑based environments
Leading and mentoring analysts and junior data scientists
Partnering closely with Risk, Technology, and Business stakeholders
Ensuring models meet governance, performance, and scalability standards


What We Are Looking For


6 - 8+ years relevant experience, with demonstrated technical leadership
Strong hands‑on experience building machine learning and data science models end‑to‑end
Proven use of techniques such as:
Boosting algorithms (XGBoost, CatBoost)
Neural networks
Clustering and anomaly detection
Advanced proficiency in Python
Solid experience with SQL and working with large, complex datasets
Ability to lead technically while remaining actively involved in modelling work
Experience within credit risk, propensity modelling, or financial crime analytics
Experience with independent validation of models and/or detailed peer review
Proven experience researching machine learning models


Qualifications


Honours or Master's degree in Mathematics, Statistics, Computer Science, Actuarial Science, or a related quantitative field


Preferred/ Ideal


Experience leading or building ML teams in a regulated environment
Experience deploying or supporting models in cloud environments
Exposure to credit risk modelling, scorecards, or IFRS‑related analytics
Financial crime (fraud or AML) modelling experience
Experience designing models with scalability and deployment in mind
Familiarity with model risk, governance, or validation standards