Senior Data Scientist

Responsibilities:

• Build predictive models for learner outcomes: dropout risk, knowledge gaps, learning pace, and content recommendation.
• Design and analyse A/B experiments with rigorous statistical methodology and business metric alignment.
• Analyse large-scale learner interaction datasets to surface actionable patterns for product and curriculum teams.
• Develop and ship ML solutions end-to-end: from exploration to serialised models, API wrappers, and monitoring.
• Build dashboards and data narratives that communicate findings clearly to non-technical stakeholders.
• Partner with engineering on feature store design and pipeline automation for recurring model inputs.
• Run causal inference analyses to attribute learner outcomes to specific interventions or content changes.
• Document model assumptions, evaluation results, and limitations clearly for cross-functional review.
• Leverage cloud platforms and data pipelines to build, deploy, and monitor ML models in production environments.
• Build data visualisations and analytical reports that communicate findings clearly to non-technical product and government stakeholders.

Requirements:

• Strong knowledge of machine learning, statistics, and data analysis.
• Proficiency in Python, SQL, and data science libraries.
• Experience with data preprocessing, feature engineering, and model development.
• Knowledge of predictive analytics, AI/ML models, and model evaluation.
• Experience working with large datasets and data visualisation tools.
• Understanding of cloud platforms and data pipelines is preferred.
• Strong analytical, problem-solving, and communication skills.

Preferred Skills:

• MLOps basics: model serialisation, deployment patterns, monitoring and drift detection.
• Deep learning fundamentals: when to apply neural approaches vs classical ML.
• GenAI applications: LLM-based classification, semantic similarity, and ranking for data science tasks.
• Experimentation platform design: building and maintaining self-serve A/B testing infrastructure.
• Business analytics: funnel analysis, retention modelling, cohort analysis, LTV estimation.