Senior Data Scientist — Clean Cooking (PAYG LPG)

• Develop a deep understanding of customer and commercial needs by engaging with sales agents and customers.
• Translate business challenges into clear statistical questions and communicate findings to both technical and non-technical stakeholders.
• Prioritise data product development based on potential impact on activation, refill frequency, retention, or unit economics.
• Manage expectations, scope, and timelines for your data product workstreams.
• Design, build, and evaluate machine learning models for key business use cases such as churn prediction, credit behaviour, demand forecasting, and customer segmentation.
• Apply probabilistic and Bayesian methods to quantify uncertainty and support decision-making.
• Design and analyse experiments including A/B tests and quasi-experiments under field conditions.
• Perform exploratory data analysis, feature engineering, and data wrangling on large datasets.
• Collaborate with data engineering teams to ensure smooth deployment and monitoring of models.
• Track model performance, identify degradation, and recommend retraining or redesign as needed.
• Maintain clean, reproducible, and well-documented code following team standards.

• Degree in Computer Science, Statistics, Mathematics, Engineering, Economics or a related quantitative field; advanced degree is a plus but not required.
• 5 to 8 years of hands-on experience in data science or applied machine learning roles, with at least 2 years owning data products end to end.
• Proven track record of delivering data products that have measurably impacted business outcomes.
• Strong communication skills to explain complex concepts to non-technical commercial leaders.
• Experience managing product needs, trade-offs and delivery timelines with senior stakeholders.
• Expertise in classical machine learning methods including gradient boosting, regression, clustering, ranking, and time-series forecasting.
• Solid knowledge of probabilistic modelling, Bayesian inference, and uncertainty quantification, with experience using probabilistic programming languages like PyMC or Stan.
• High proficiency in Python and strong SQL skills, including complex queries and window functions.
• Experience with model evaluation techniques such as cross-validation and calibration, focusing on business-relevant metrics.
• Experience in experiment design and statistical hypothesis testing.
• Comfortable working with cloud data warehouses and experiment tracking tools (AWS and MLflow preferred).
• Preferred: Experience in pay-as-you-go (PAYG), fintech lending, telco, or emerging-market consumer businesses.
• Preferred: Knowledge of survival modelling, causal inference, marketing mix modelling, operations research, or optimisation methods.
• Preferred: Familiarity with MLOps and model deployment on AWS services such as SageMaker, Lambda, and ECS.

The advert mentions professional growth opportunities, a collaborative and multicultural work environment, and structured learning and development programs through the Sun Center for Leadership.