SUMMARY:
Do you dream in data and think in probabilities? Here’s your chance to turn that analytical superpower into impact! We’re looking for a creative and technically brilliant Application Scoring Specialist who can build predictive models that shape smarter, faster, and fairer lending decisions. This is not a tick-box modelling role — it’s your chance to lead innovation in credit risk and application scoring across multiple industries.
POSITION INFO:
Application Scoring Specialist
Experience Level: Senior (8+ years)
Join a dynamic, data-driven organisation that’s redefining the future of lending and credit analytics across Africa. You’ll work with passionate Data Scientists, Analysts, and risk experts who thrive on solving complex problems in low-data environments — particularly in the SME sector, where creativity and precision truly matter.
This is a hybrid role, perfect for someone who wants to blend deep technical work with strategic influence. You’ll design, test, and deploy cutting-edge scorecards that directly impact multi-million-rand lending portfolios. Plus, you’ll mentor future data talent while shaping the scoring strategy of the future.
If you’re driven by challenge, collaboration, and making data tell its story, this is your stage.
Key Responsibilities:
- Design and develop robust application scorecards, including reject inference and model validation.
- Lead feature engineering initiatives that push model accuracy and business value forward.
- Innovate in data-scarce environments, especially within SME lending.
- Partner with senior stakeholders to align technical models with strategic goals.
- Mentor and guide Junior Analysts, fostering a culture of technical excellence.
- Drive best practices in model governance and deployment.
- Deliver insights and recommendations to senior leadership in a compelling, story-driven way.
Job Experience and Skills Required:- Bachelor’s Degree in Mathematics, Statistics, Actuarial Science, Data Science, or a related field.
- 8+ years of hands-on experience in application scoring and credit risk modelling.
- Deep expertise in feature engineering, scorecard design, reject inference, and validation.
- Strong technical proficiency in SAS (required) and Paragon Modeler (advantageous).
- Track record of developing models across multiple industries (e.g., retail, fintech, telecoms, or insurance).
- Skilled at working with limited datasets to deliver robust, scalable solutions.
- Excellent communication skills and the confidence to influence executives.
- Leadership experience in mentoring, teaching, or developing teams.
Preferred Attributes:- Experience in SME or alternative credit scoring.
- Knowledge of PD and behavioural model development.
- Familiarity with modern data science and machine learning techniques.
- Comfort in fast-paced, agile, and cross-functional environments.
Why Join Us?:- Work on high-impact projects that transform the credit and SME lending landscape.
- Be part of a data team that values innovation, collaboration, and real-world impact.
- Hybrid flexibility and autonomy to design, lead, and deliver projects your way.
- Competitive rewards and the chance to influence how credit scoring evolves in emerging markets.
Apply now!
For more exciting
Finance vacancies, please visit:
/>
I also specialise in recruiting in the following:
- Actuarial roles (Life, Short-Term, Health, Pensions, Quantitative)
- Data Scientists / Data Analysts (Python, R, SQL, Machine Learning)
- Risk Analysts (Credit, Market, Model Risk, Operational)
- Pricing Specialists (Insurance, Financial Products)
- Machine Learning & AI Data Scientists (ML Ops, NLP, Predictive Modelling)
- Quantitative Specialists across Banking, Insurance, and FinTech
If you have not had any response in two weeks, please consider the vacancy application unsuccessful. Your profile will be kept on our database for other suitable roles.
For more information, contact:
Heidi Joubert
Specialist Recruitment Consultant
Connect with me on LinkedIn!
NB! This job is now closed. You can apply for other jobs by uploading your CV.
