Description: What you need to have: * Experience in Python to build and deploy complex machine learning models at scale. * Proficiency in managing the machine learning model lifecycle and best practices for deployment. * Extensive experience with Databricks for building end-to-end machine learning pipelines. * Advanced knowledge of data virtualization tools such as Denodo for efficient data access. * Proficiency in Teradata to optimize data storage and query performance. * Leadership skills to lead MLOps initiatives and drive innovation in machine learning operations. * Strategic thinking to align MLOps processes with business objectives and goals. * Excellent communication and stakeholder management skills across all organizational levels. * Ability to navigate complex technical challenges and deliver effective solutions. * Resilience and adaptability to thrive in a dynamic, fast-paced environment. Required technical skills: * Classification models (trees, ensembles, logistic regression, etc.) * Evaluation metrics (AUC, Precision, Recall, F1, KS, etc.) * Techniques for handling extreme class imbalance (SMOTE, undersampling, oversampling) * Data cleaning, transformation, and feature engineering * Knowledge of transactional and financial data * Advanced use of MLflow for experiment tracking and logging * Unity Catalog for model registration * Model versioning (metric validation, model promotion) * Model serving for production deployment * Hyperparameter optimization (Grid Search, Random Search, Hyperopt, Optuna) * Threshold calibration (e.g., CalibratedClassifierCV) * Spark for large-scale processing (SparkSQL, PySpark) * Automation of training and deployment pipelines * GitLab for project versioning * Databricks as the development platform What you will do: * Lead highly complex analytical projects, from conception through delivery of solutions that generate measurable value for the organization. * Design and implement advanced machine learning models, considering aspects such as scalability, governance, fairness, and explainability. * Mentor junior data scientists, promoting technical upskilling, reviewing deliverables, and supporting career development. * Define technical standards and best practices, contributing to the maturity of the team and consolidation of a robust analytical culture. * Engage with strategic stakeholders, translating business needs into data-driven solutions and influencing high-impact decisions. * Ensure model quality, performance, and sustainability by monitoring results and proposing continuous improvements. * Participate in strategic and technical forums, representing the data science function and contributing to alignment with the organizational vision. * Document and share learnings, strengthening the knowledge repository and promoting continuous team evolution. 2512240202491933705