Role Summary :

Build and maintain machine learning models for forecasting and predictive use cases (demand, revenue, churn, anomaly detection, supply chain) from data preparation, data analysis, feature engineering and model selection through validation, deployment and drift/bias monitoring.

Key Responsibilities :

- Develop forecasting and predictive models end-to-end: features, selection, validation, deployment.

- Backtest rigorously with holdout sets and confidence intervals.

- Monitor deployed models for drift and retrain on a defined cadence.

- Work with Data Engineers to source and shape reliable training data.

- Translate forecasting needs from the Business Analyst and Product Manager into models that ship.

What We Expect From You :

- Choose the simplest model that meets the accuracy bar; favor explainability and maintainability.

- Be upfront about a model's limitations, not just its headline accuracy.

- Treat deployment as the start of monitoring, not the finish line.

- Communicate forecasts and their uncertainty in terms a business stakeholder can act on.

Qualifications & Skills :

- 4 - 7 years in applied data science with production ML deployments.

- Exposure to Pharma industry preferred.

- Strong statistics, time-series forecasting, machine learning algorithms and model validation practice.

- Python (pandas, scikit-learn or equivalent), SQL; MLOps exposure preferred.

- Clear communication of quantitative results to non-technical audiences.