ML Engineer | Forecasting & Mathematical Optimization

• Participation in a strategic project for the banking sector.

• Joining a technological environment with real Machine Learning and optimization challenges.

• Work with technologies such as Python, Machine Learning, Databricks, PySpark, and MLflow.

• Professional development in Data Science and Artificial Intelligence projects.

Are you interested in working on projects where predictive models and mathematical optimization have a direct impact on decision-making?

We want to meet you!

At Tecdata Engineering, we are looking for an ML Engineer | Forecasting & Mathematical Optimization!

At Tecdata Engineering, we are looking for a Machine Learning Engineer to participate in a strategic project within the banking sector, collaborating on the development, analysis, and improvement of Machine Learning models oriented towards demand forecasting, time series analysis, and mathematical optimization.

We are looking for a profile with a solid analytical foundation and practical experience in traditional Machine Learning, especially in the training, validation, and optimization of predictive models. You will participate in a cash management use case for a top-tier banking entity such as Santander.

The productization and MLOps aspect will also be present, although the main focus will be on knowledge of predictive models, time series, and optimization techniques.

• Design, train, validate, and optimize supervised Machine Learning models.

• Develop and analyze forecasting models for demand forecasting using time series analysis techniques.

• Evaluate model behavior, analyze performance metrics, and propose improvements in their accuracy and stability.

• Apply mathematical optimization techniques, mathematical programming, and heuristics to solve business problems and support operational decision-making.

• Combine predictive models with optimization models to improve planning and resource allocation.

• Analyze and improve existing models, evaluating different algorithms, variables, and training strategies.

• Participate in the adaptation and productization of models in corporate environments.

• Collaborate in the implementation of training and inference pipelines using Python, PySpark, and Databricks.

• Work with tracking, versioning, and model management tools such as MLflow.

• Apply best practices in development, testing, traceability, and monitoring.

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