Data Scientist (Banking Portfolio)

GoTyme ZA (South Africa); Cape Town; On-site; ZAR 600,000 - 1,300,000; Full time

Job summary

GoTyme ZA (South Africa) seeks a Data Scientist to own the end-to-end credit risk management for the FNB MCA portfolio, including strategy, modelling, and governance. You will partner with Risk, Data Science, and business stakeholders to drive measurable impact.

Requirements include 3–5 years in credit risk or data science within financial services, strong SQL and Python skills, and familiarity with IFRS 9. You will operate in a focused, autonomous role with cross-functional collaboration.

Qualifications

• Degree in mathematics, statistics, data science, or related quantitative field.
• 3–5 years of credit risk analysis or data science experience in banking, lending, fintech, or financial services, including independent delivery of credit risk work.
• Strong understanding of credit risk strategies, scorecards, models, and ML techniques for credit decisioning.
• Familiarity with IFRS 9 principles and their application to credit risk management, including ECL calculations.
• Strong analytical skills with the ability to interpret complex financial and trade data and make informed decisions.
• Proficiency in SQL and Python; Databricks experience is advantageous.
• Excellent communication and presentation skills for non-technical stakeholders.
• Ability to work independently, structure ambiguous problems, take ownership, and manage multiple priorities.

Responsibilities

• Own end-to-end credit risk management of the FNB MCA portfolio, driving the work plan with Risk and Data Science teams.
• Monitor portfolio performance, identify trends and risks, and recommend mitigation or growth actions.
• Set and manage the portfolio’s credit risk strategy, policy, and decisioning rules within risk appetite.
• Develop, maintain, implement, and monitor scorecards and credit risk models across the lifecycle.
• Ensure models are developed, reviewed, documented, and governed per model risk standards.
• Support model validation with clear documentation, data definitions, assumptions, and results.
• Collaborate with data engineering to deploy models and decisioning logic to production.
• Prepare and present reports to senior management with key risk metrics and recommendations.
• Develop stress testing scenarios and conduct sensitivity analyses for portfolio resilience.
• Monitor regulatory changes, especially IFRS 9, and ensure compliant reporting.

Skills

SQL

Python

Credit risk

Modeling

IFRS9

Education

Quantitative degree

Tools

Databricks

Job description

Overall Purpose of the Role:

As a Data Scientist, you will play a key role in shaping the credit risk strategy for GoTyme Bank’s partnership with FNB, which provides Merchant Cash Advances (MCAs) to SME merchants.

Working in a focused, agile team within the broader Data Science function, you will take end-to-end ownership of credit risk across the FNB MCA portfolio—from strategy, monitoring and modelling to implementation, governance and decision support. Your insights will directly influence credit decisions, portfolio performance and our ability to support the growth of SMEs.

This is an exciting opportunity for a driven Data Scientist who enjoys autonomy, solving complex problems and collaborating with Risk, Data Science and business stakeholders to deliver measurable impact.

Experience and Skills Required:

• Degree in mathematics, statistics, data science, or a related quantitative field.
• 3–5 years of credit risk analysis or data science experience in banking, lending, fintech, or financial services, including independent delivery of credit risk work.
• Strong understanding of credit risk strategy, scorecards, models, and machine learning techniques for credit decisioning.
• Familiarity with IFRS 9 principles and their application to credit risk management, including expected credit loss (ECL) calculations.
• Strong analytical skills with the ability to interpret complex financial and trade data and make informed decisions.
• Proficiency in SQL and Python is essential; experience with Databricks is advantageous.
• Excellent communication and presentation skills, with the ability to convey complex concepts to non-technical stakeholders.
• Ability to work independently, structure ambiguous problems, take ownership, and manage multiple priorities effectively.
• Strong testing discipline, including data quality checks, reconciliation, and implementation testing.
• Familiarity with SME lending, including industry-specific risk factors, is highly desirable.
• Proficiency in advanced analytics and the responsible use of AI tools is essential.

Responsibilities:

• Own the end-to-end credit risk management of the FNB MCA portfolio, independently driving the work plan while collaborating with the wider Data Science and Risk teams.
• Monitor portfolio performance, identify trends and emerging risks or opportunities, and recommend appropriate risk mitigation or growth actions.
• Set and manage the portfolio’s credit risk strategy, policy, and decisioning rules, balancing risk, growth, and commercial objectives within agreed risk appetite.
• Develop, maintain, implement, and monitor scorecards and other credit risk models and methodologies across the credit lifecycle.
• Ensure that all data science models are developed, reviewed, documented, and governed in line with the bank’s model risk management standards.
• Support independent model validation activities by providing clear development documentation, data definitions, assumptions, limitations, methodology rationale, and performance results.
• Work with data engineering and technology teams to support the deployment of models and decisioning logic into production environments, including implementation testing and reconciliation.
• Collaborate with cross-functional stakeholders, including Finance, Operations, and Compliance, to align portfolio and risk management objectives.
• Prepare and present reports to senior management, highlighting key risk metrics, trends, and recommendations.
• Develop stress testing scenarios and sensitivity analyses to assess the resilience of the FNB MCA portfolio under various economic conditions.
• Monitor changes to regulatory frameworks, particularly IFRS 9 requirements, and ensure compliance in credit risk management practices and reporting.