Felipe Cueto

I’m a Data Engineer with a background in Electronic and Electrical Engineering and experience turning data into trusted, decision-ready systems. I work across ETL, data modeling, pipelines, and quality practices—especially when I can combine structured data with AI to automate analysis and organization.

At Experis/Promigas, I designed and built Azure data pipelines with centralized data storage, cloud configuration, and API integration. I also developed natural language and speech processing models and built a Retrieval-Augmented Generation system on the Databricks Lakehouse using Apache Spark pipelines.

At Procibernética, I modeled and transformed data for 15+ clients using PySpark, Google Cloud, BigQuery, and BI tools—reducing errors and improving decision-making. I also automated big data quality review and correction on Azure, and leveraged LLMs to extract and classify text from up to 20,000 documents, cutting manual processing time by 65%.

Earlier, as a freelance Data Engineer, I built real-time monitoring and automation solutions for cacao fermentation and programmed an autonomous robot in Python to track and map routes. I’m especially proud of my focus on accuracy (over 99% dataset accuracy) and reliability—backed by governance, auditing, and continuous improvement.