Vitor Rosa

I am responsible for designing, developing, and maintaining AI-powered recommendation engines for the company’s e-commerce. While the data scientists on my team build the models, I focus on integrating them into a scalable architecture and deploying them through APIs.

I worked as a Data Scientist in the Data Science and Advanced Analytics team, driving user experience personalization on the company’s digital platforms. By developing and integrating machine learning, deep learning, and LLM-based models into our recommendation system, I contributed to improving customer engagement and business performance.

My primary goal was to drive the company's financial objectives by leveraging data-driven approaches with a strong focus on artificial intelligence (AI). I worked on projects within the CRM domain, specifically on initiatives related to Shell Box— a fueling application that generated annual revenue in the billions of BRL.

Leveraging data science to drive financial returns by specializing in recommendation engines through collaborative and content-based filtering.

Work carried out on historical data of industrial processes in the food sector. The aim was to optimize dairy production based on a concept: to produce just enough with the best quality possible and at the lowest cost.

The work aimed to explore AI-based solutions that are potentially more efficient in the predictive maintenance program of companies whose mechatronics sector at the Universität Paderborn provides consultancy.
The technical objective, in essence, consists of predicting, as accurately as possible, the remaining useful life of mechanical components submitted to constant stress, and, in case of failures, determining the dimensions and characteristics of the failures (cracks).

Development, optimization and research of machine learning models focused on demand forecasting and anomaly detection in energy supply data.