Responsibilities & achievements

• I developed and deployed the structural parts. Currently, I am working on data cleaning and transformation with two more data engineers whom I have been training. • Boosted Spark Jobs' performance on Databricks by optimizing queries, data caching, table partitioning, cluster resizing, and query improvements, resulting in a substantial reduction in execution time and computational costs. • Improved data governance in the company's Big Data environment by implementing a Data Catalog service (Unity Catalog), an observability tool for clusters and jobs (Overwatch), and personalized access controls for internal and external data based on users and areas. • Created data quality validation and data cleaning processes that drastically reduced the ticket opening rate related to data quality. • Reduced the average execution time of the main ELT pipeline in the legacy environment from 12 to 7 hours by reformulating the orchestration, tuning SQL procedures, and identifying and removing unnecessary steps.

Responsibilities & achievements

• Completed a predictive time series analysis project, which delivered a 12% improvement in refractory material consumption forecasts.

Responsibilities & achievements

• Developed a model that identifies possible tax evasion fraud on national steel imports. In the first 6 months, more than 30 confirmed cases of fraud were identified by the model. • Joined the company's Innovation Ambassadors team, becoming the point for data solutions.

Responsibilities & achievements

• Improved the visibility of growth and fluctuation of steel demand by customers, with a predictive modeling of Machine Learning. • Developed a People Analytics project with the HR team, helping them to identify professional profiles and control the turnover of more than 14 thousand employees.