Data Professional | Engineering · Science · Analytics
I combine an appreciation for efficiency from Production Engineering (PUC-SP) with the analytical depth of Data Science (PUC-RS). I used both sides to translate complex operations into information ecosystems in three experiences at leading global companies in their sectors: IBM, Keyence and Thermo Fisher Scientific.
My pillars are building ETL pipelines, data modeling for analytical process automation, and developing predictive analyses and models — structuring raw data into reliable databases with a focus on consistency, scalability and measurability.
Experienced at global market leaders
Production-grade solutions implemented at global companies.
A Python-based framework that automated 40 SAP reporting workflows without API dependency to unify company data into a select number of extractions from SAP inside a centralized and auditable Data Warehouse.
A classification model prioritizing companies within the active customer base, integrating sales activity, purchase history, geographic variables and inputs from sales leadership to optimize field team deployment and targeted marketing campaigns
Showcase of end-to-end data, AI and analytics solutions. Architecture, automation, machine learning and business intelligence.
End-to-end SQL analytics on a synthetic sales dataset — business KPIs, cohort analysis, ranking windows, and executive reporting without a single line of Python.
Automated pipeline fetching, transforming, and storing data from a public REST API on a recurring schedule — with pagination, error handling, and structured database storage.
Full data science workflow on a classification problem — exploratory analysis, feature engineering, model training, hyperparameter tuning, and interpretable evaluation reporting.
A fully deployed interactive web application for data exploration and visualization — built with Streamlit and accessible to non-technical stakeholders through a public URL.
Available for opportunities, freelance projects and collaboration.
