Senior Data Scientist

Cape Town based candidates only. Job Overview The Senior Data Scientist will be responsible for developing, validating, and operationalizing advanced machine learning and AI models that support strategic business outcomes across the retail value chain including customer segmentation, demand forecasting, price optimization, and recommendation systems. The role requires a combination of strong technical expertise, business acumen, and leadership skills, with the ability to translate analytical outcomes into actionable business strategies for diverse stakeholders. Key Responsibilities Data Science & Modelling: Design, develop, and deploy machine learning models for key retail use cases such as customer segmentation, churn prediction, product affinity, and demand forecasting. Apply unsupervised and supervised learning techniques (e.g., clustering, regression, decision trees, ensemble methods, NLP, deep learning) to large‑scale structured and unstructured datasets. Build and maintain predictive models and experimentation frameworks to improve forecast accuracy and optimize marketing, pricing, and inventory decisions. Conduct feature engineering, model validation, and performance tuning to ensure accuracy, interpretability, and scalability. Integrate LLMs and generative AI tools where relevant to enhance analytics, reporting, and customer‑facing automation (e.g., chatbots, product search). Partner with key business stakeholders (Marketing, Supply Chain, Merchandising, Finance) to translate analytical outputs into strategic recommendations. Lead the creation of customer and product segmentation frameworks that drive targeted campaigns, loyalty engagement, and personalized promotions. Collaborate with cross‑functional data teams (Engineering, BI, Cloud) to ensure data availability, integrity, and governance. Support data storytelling and insight visualization through dashboards, visual models, and presentations to non‑technical audiences. Define and implement model validation, bias detection, and guardrail testing to ensure AI model reliability, fairness, and brand alignment. Drive continuous improvement in model performance through automation, monitoring, and A/B testing. Establish documentation and version control standards across ML pipelines for transparency and reproducibility. Mentor junior Data Scientists and Analysts, fostering a culture of experimentation and innovation. Contribute to the development of ML Ops standards, CI/CD pipelines, and deployment automation within the data science environment. Collaborate with external vendors and research partners to evaluate new techniques and tools. Required Skills & Experience Strong programming skills in Python (Pandas, NumPy, Scikit‑learn, TensorFlow, PyTorch, Statsmodels). Experience with SQL and working knowledge of data pipelines and cloud environments (AWS / Azure / GCP). Proficiency in data visualization tools (Power BI, Tableau, Matplotlib, Seaborn). Solid understanding of machine learning algorithms, statistical modeling, and time‑series forecasting. Exposure to LLM validation, prompt engineering, and RAG frameworks will be highly advantageous. Prior experience applying data science within retail, e‑commerce, FMCG, or financial services preferred. Proven ability to translate analytical findings into business value (customer retention, campaign optimization, operational efficiency). Strong communication skills and comfort engaging senior business stakeholders. Qualifications MSc or equivalent in Data Science, Computer Science, Artificial Intelligence, or Applied Mathematics. (advantageous) years experience in a data science or ML engineering role, preferably within large‑scale data environments. #J-18808-Ljbffr