Job Description

• We’re looking for a data scientist to join our technology team. You’ll leverage cutting-edge cloud technology and work on exciting challenges that directly impact business decisions and user experiences. The position is based at our Cape Town or Randburg offices.

WHAT YOU’LL DO

Machine learning & automation

• Design, build, test and optimise predictive models that deliver automated business intelligence
• Develop sophisticated algorithms to solve complex business challenges
• Deploy and monitor ML models in production environments with proper versioning and tracking

MLOps & model lifecycle management

• Track model performance, detect drift and manage model retraining workflows
• Containerise ML applications and manage model versioning across environments
• Partner with cross-functional stakeholders to identify, scope and solve critical business problems
• Create automated reporting systems and interactive dashboards that empower data-driven decision making
• Monitor platform performance and establish key performance metrics

Analytics & insights

• Analyse diverse data sources including custom analytics, paywall metrics, and web analytics to uncover actionable business insights
• Conduct deep-dive user behaviour analysis to enhance UX and drive engagement
• Data engineering & pipeline development
• Build and maintain robust data pipelines for ingesting, processing and transforming large datasets
• Ensure data quality and implement validation checks across data workflows
• Design efficient ETL/ELT processes to support analytics and ML initiatives

EDUCATION & EXPERIENCE

• Honours degree (minimum) in Data Science, Mathematics, Statistics, Engineering or related field
• 3+ years of hands-on Python development experience
• Proven experience with big data technologies and cloud platforms

Technical expertise

• Development Tools: Git version control, Jupyter Notebooks, Docker
• ML Frameworks: scikit-learn, PyTorch, TensorFlow, LightGBM, XGBoost, Pandas
• Data Engineering: SQL, DAG orchestration tools, data pipeline design, ETL/ELT processes
• Statistical Methods: Linear/logistic regression, statistical analysis techniques
• Recommendation Systems: Collaborative filtering, content-based and hybrid models
• Tree-Based Methods: Random Forests, decision trees, gradient boosting
• Advanced Techniques: Clustering algorithms, Natural Language Processing (bag-of-words, word embeddings, transformer models)
• Model Deployment: Production deployment, A/B testing, model monitoring and maintenance

Data engineering skills

• Strong SQL proficiency and database design principles
• Experience with data warehousing concepts and dimensional modelling
• Knowledge of data quality frameworks and validation processes
• Understanding of streaming vs. batch processing architectures

Mindset

• Curiosity and eagerness to learn emerging technologies, platforms and methodologies
• Problem-solving approach with attention to detail and business impact
• Strong collaboration skills for working across engineering and business teams