I am an Electrical Civil Engineer and Master in Data Science with a hybrid background in electrical systems, data science, and MLOps. I specialize in transforming complex industrial data into actionable intelligence for high-impact operational challenges.
My main focus is predictive maintenance, prognostics and health management (PHM), remaining useful life estimation, battery management systems, and time-series analytics. I work with noisy, heterogeneous industrial data to improve asset reliability, safety, and operational efficiency.
I am currently developing real-time battery-health monitoring solutions for electric vehicle fleets in underground mining, collaborating directly with Codelco. My work includes scalable data ingestion, storage, ETL orchestration, machine learning pipelines, and signal-quality processing.
I have experience designing end-to-end data products, from data acquisition and web scraping to predictive models, APIs, dashboards, and production-ready infrastructure. I have processed datasets ranging from millions to more than 75 million records.
I am proficient in Python, SQL, machine learning, deep learning, data engineering, cloud services, and MLOps tooling. I am motivated by building practical, scalable systems that create measurable value in electromobility, mining, and other industrial environments.
I contributed to the development of SmartLoader, a SaaS solution for forecasting failures in front loaders using multimodal learning strategies.
I designed data pipelines to integrate heterogeneous sources, including PostgreSQL and time-series data. I packaged models with Docker and FastAPI to support predictive-maintenance workflows intended to reduce mining operational costs.
I develop a scalable, real-time monitoring system for battery health, including state of charge and state of health, for underground-mining electric vehicle fleets in collaboration with Codelco.
I design and deploy MLOps architecture using Apache Kafka for ingestion, TimescaleDB for time-series storage, and Apache Airflow for ETL and machine-learning orchestration. I engineered a backfill process for more than 75 million records and achieved over 89% data compression, reducing storage from 10.56 GB to 1.15 GB.
I apply signal-processing techniques to address industrial data-quality issues such as signal loss, noise, and quantization.
I led the data-acquisition strategy, processing more than 150,000 electricity bills through web scraping.
I developed an end-to-end data product with predictive models and interactive Plotly/Dash dashboards. I also managed and optimized a database containing millions of records.
I developed Python scripts to automate critical invoicing and data-analysis processes, reducing manual operational time.
I optimized data pipelines and SQL database queries to improve the efficiency and speed of internal reporting.
I configured and provided remote support for the installation of technological solutions across more than 20 branches.
I used AWS and JSON to manage IoT devices and analyze their performance.
Master in Data Science, Data Science
Electrical Civil Engineer, Computational Intelligence
Major in Computational Intelligence.
This professional hasn’t added portfolio projects yet.
This professional hasn’t listed any services yet.
