ML Engineer – Forecasting, Optimization and MLOps

We are looking for an ML Engineer with experience in the productionization of Machine Learning models, demand forecasting, and optimization models to join a project in the banking sector.

The person will participate in the industrialization of already developed models, working to bring them into production environments with guarantees of robustness, scalability, traceability, and maintainability.

The main objective will be to transform analytical models into production-ready solutions, collaborating on the improvement of demand forecasting models based on time series and optimization models applied to operational decision-making.

• Productionize existing Machine Learning models, adapting them to the technical and operational standards of the banking environment.

• Analyze and improve forecasting and demand forecasting models based on time series.

• Design and adapt training, inference, and prediction generation pipelines.

• Work with Azure Databricks and PySpark environments.

• Evaluate retraining strategies, model updates, and artifact persistence.

• Participate in the optimization of models and operational decisions, including denomination optimization.

• Integrate models with MLflow and corporate governance and deployment tools.

• Apply MLOps best practices: versioning, testing, CI/CD, monitoring, and traceability.

• Diagnose production incidents and perform root cause analysis.

• Collaborate with Data Engineering, Data Science, Platform, and Business teams.

• Document solutions, technical decisions, and operating procedures.