Senior Credit Data Scientist

When it comes to putting people first, we're number 1. 

The number 1 Top Employer in South Africa. 
Certified by the Top Employer Institute 2026. 

Role Purpose/Business Unit:

We are looking for an experienced Senior Data Scientist to join our team. The successful candidate will be responsible for designing and implementing credit scorecards using machine learning models, using big data tools such as Spark and Python to analyze large volumes of data, and developing algorithms that drive business decisions. The candidate must have excellent skills in mathematics, statistics, and AI, as well as a keen interest in data science and problem-solving.

Your responsibilities will include:

• Develop and maintain credit scorecards and risk assessment models to evaluate the creditworthiness of customers applying for handset financing and loan facilities.
• Conduct thorough statistical analysis to identify relevant credit risk indicators and patterns, using large datasets.
• Collaborate with cross-functional teams, including data scientists and business stakeholders, to gather requirements and fine-tune credit scorecard models according to business needs.
• Developing predictive models with large and varied datasets, working with a community of colleagues across Big Data and customer functions.
• Contributing to the wider community to enable Machine Learning and AI capability across Vodafone globally.
• Development of machine learning models for various areas of the business on the Big Data Platform
• Development of prototype code in e.g. PySpark for automated training and scoring of the machine learning models
• Machine Learning Model performance tracking and reporting using e.g. Qlik
• Uses data visualisation to engage audience in a compelling way, enabling effective storytelling
• Work with lead data scientist to deliver key packages of work to meet the needs of business customers
• Works in partnership with Big Data Engineering for data ingestion to support use cases
• Works in partnership with Big Data Production Data Engineering for model automation and productionising 
• Deploy models in Containerized Environments using tools such as Docker and Kubernetees , allow for on-prem and on Cloud Deployment.
• Developing insightful dashboard to enable faster decision making
• Identifying new data sources and evaluate emerging technologies for data discovery usage.
• Mentoring young data scientists in the team, presenting the results to technical and non-technical audiences

The ideal candidate for this role will have:

• Bachelor’s or Master’s Degree in quantitative fields like Mathematics, Statistics, Economics, Computer Science Engineering, Artificial Intelligence or related fields (essential)
• A minimum of 5 years relevant experience in Data Science
• Experience working with and managing a team of junior data scientists
• Experience in data manipulation: use of structured data tools (e.g., SQL), and unstructured data platforms (e.g., Hadoop, Spark, NoSQL)
• Proficiency in at least one relevant programming language
• Experience in major machine learning modelling libraries (e.g., H2O, scikit-learn, PyTorch, Tensorflow) and techniques (e.g. random forest, gradient boosting, k-means segmentation, multiple regression, factor analysis, time-series forecasting)
• Exposure to cloud native deployment of models and working with Containerised technologies such as Docker and Kurbernetees.
• Knowledge of MLOPS concepts and deployment of models through batch and real-time architectures. Use of Technology such as (MLFLOW and Apache Airflow)
• Familiarity with visualisation tools (e.g. Tableau, Qlik, D3, Apache Superset, Plotly)
• Exposure/interest in machine learning 
• Professional and/or academic experience in Big Data analytics & deployment of models and algorithms to solve real-world problems (with deep statistical and  machine learning modelling expertise)
• Experience manipulating and analysing large and complex datasets /
• Experience in visualisation, creating graphical static and interactive displays of data that clearly communicate insight (preferred)
• Good interpersonal communication and presentation skills
• Ability to work in a fast-paced environment
• Analytical and expansive thinking with a strong desire to deliver and develop

Key Skills

• Credit Scorecard Development: Proven experience in developing credit scorecards in the financial services or telecommunications industry.
• Statistical Analysis and Modeling: Data Scientists should have a strong background in statistical methods and modeling techniques. This includes knowledge of regression analysis, time series analysis, hypothesis testing, and other relevant statistical tools to develop accurate credit risk models.
• Machine Learning and Data Mining: Proficiency in machine learning algorithms and data mining techniques is crucial for building predictive models and identifying patterns in large datasets.
• Programming Skills: Data Scientists should be proficient in programming languages commonly used in data analysis, such as Python (prefered) or R. Additionally, familiarity with libraries and frameworks like scikit-learn, TensorFlow, or Keras is beneficial.
• Data Manipulation and Visualization: Data cleaning, preprocessing, and transformation are critical steps in credit risk modeling. Experience with data visualization tools (e.g., Matplotlib, ggplot, or Tableau) is also valuable to communicate results effectively.
• Domain Knowledge in Credit Risk: Understanding the financial industry, credit risk principles, and relevant regulations is essential. Knowledge of credit scoring, credit scoring models (e.g., logistic regression, decision trees), and default prediction is a must.
• Database and SQL Knowledge: Data Scientists should be comfortable working with relational databases and be adept at writing complex SQL queries to retrieve and manipulate data.
• Big Data Technologies: Familiarity with big data technologies such as Hadoop, Spark, or NoSQL databases can be advantageous when dealing with large-scale credit risk datasets.

• Model Validation Techniques: Experience in model validation and performance evaluation is crucial to ensure the accuracy and reliability of credit risk models.
• Risk Management Concepts: Understanding risk management concepts, including Basel Accords (Basel I, II, III) and stress testing, is beneficial for developing models that comply with regulatory standards.
• Business Acumen: Data Scientists should have a strong business acumen to understand the implications of credit risk models on a company's overall strategy and decision-making process.
• Collaboration and Communication: Effective communication skills are essential for Data Scientists to explain complex models and insights to non-technical stakeholders, including business leaders and risk management teams.
• Continuous Learning: The field of data science and credit risk modeling is constantly evolving. Data Scientists need to stay updated with the latest advancements, research, and best practices in the industry.

We make an impact by offering:

• Enticing incentive programs and competitive benefit packages
• Retirement funds, risk benefits, and medical aid benefits
• Cell phone and data benefits, advantages fibre connection discounts, and exclusive staff discounts offered in collaboration with partner companies

Closing date for Applications: 16 April 2026. 

The base location for this role is Midrand, Vodacom Campus. 

The company's approved Employment Equity Plan and Targets will be considered as part of the recruitment process. As an Equal Opportunities employer, we actively encourage and welcome people with various disabilities to apply.
Vodacom is committed to an organisational culture that recognises, appreciates, and values diversity & inclusion.