Industrial Engineer · Business Intelligence & Data Analytics · Supply Chain
Knowledge management professional turning data into decisions across Sales, Operations, Planning, Supply Chain, Logistics and Market Research. AI assists the workflow.
Portfolio · LinkedIn · Lattes · GitHub
Senior BI & Analytics professional with 10+ years of experience in multinationals, retail and consulting (consumer goods, food, chemical, paper, energy and technology). Builds analytical solutions and executive dashboards with SQL, Python, Power BI, DAX, M and VBA, evolving into data pipelines on PostgreSQL with reproducible environments (Docker) and process automation (n8n). Integrates ERPs (SAP, TOTVS), ecommerce (VTEX, Google Analytics) and logistics systems (WMS, TMS, routing). Industrial Engineering background with AutoCAD for plant and DC layouts. Uses AI-assisted development to accelerate delivery while keeping modelling, data quality and business fit under human ownership.
| Domain | What it delivers |
|---|---|
| BI & Analytics | Executive reporting, KPIs and decision support for commercial, ops and planning teams |
| Data engineering | Pipelines, modelling and integration from ERP / ecommerce / logistics sources into analytical layers |
| Supply Chain & Logistics | Freight, network, inventory and DC analytics — cost, service and capacity trade-offs |
| Knowledge systems | Document RAG demos: semantic search over professional knowledge with source-aware retrieval |
| Automation | n8n workflows and AI-assisted tooling that remove manual reporting friction |
- ~90% reduction in manual reporting effort at Samsung eStore by migrating Excel workbooks to automated data pipelines and standardized Power BI (50+ reports across Sales, Marketing, CRM, Finance and Online Store).
- Roughly BRL 11.7 million logistics / freight savings and 8–12% capture in optimization projects (Galeazzi & Associates).
- ~25% stockout reduction after inventory structuring; DC layout and routing solutions for healthcare and food sectors.
- Tariff-zone redesign cutting approximately 930 zones while aligning the network for future TMS rollout.
- Credit-score ML demo: Random Forest 82.3% accuracy (vs KNN 73.4%, Logistic Regression 59.0%).
- Trained 100+ colleagues and stood up a Data Engineering & Analytics team; VTEX Key User with platform data architecture ownership.
| Project | Focus |
|---|---|
| Portfolio site | Public case studies, stack and contact |
| PBI-Projects | Power BI demos and data visualization |
| Python-ML_DS | Credit Score ML, Lotomania (DE + DS + FastAPI) |
| N8N-AI_Agents | n8n / LangChain agent workflows |
| SQL-Postgres | PostgreSQL patterns, Brazil geo dimensions (md_dim) |
Languages & analytics
SQL · Python · VBA · DAX · M
BI & visualization
Power BI · Tableau · Excel
Data & platforms
PostgreSQL · Docker · VS Code · DBeaver · pipelines · Talend · Pentaho · dbt · BigQuery (GCP)
Automation & AI-assisted workflow
n8n · Machine Learning (scikit-learn demos) · RAG / embeddings (portfolio demo)
Domain systems
SAP · TOTVS · VTEX · Google Analytics · WMS · TMS · routing tools
Industrial / layout
AutoCAD (plant & distribution-center layouts)
Data exists to drive decisions — not dashboards for their own sake.
Pipelines beat hero spreadsheets.
Supply Chain and commercial metrics belong in the same conversation.
Architecture is a business trade-off: cost, reliability and time-to-insight.
AI amplifies analysts; humans own the model and the narrative.
Turning fragmented operational data into actionable intelligence.
Open to conversations with recruiters and partners in BI, Analytics and Supply Chain.