DATA SCIENTIST - Home Office

Realizes activities in the development of new products and demands for continuous improvement of tools 1) SISMOŴDEEPBLUE, developing hydrodynamic, meteorological, and oceanographic models with Machine Learning application, for Artificial Intelligence application;

• 2) SISMOD, Development of scripts to improve the quality of data received from equipment, applying quality control techniques based on the QARTOD standard, according to the global manual of oceanic data control by NOAA;

• Realizes activities in the development of new products and demands for the SISMOŴDEEPBLUE tool, through data collection, analysis, creation of a database, model development, and validation;

• · Solves problems with oceanographic data using Data Science;
• · Assists and supports the team in cleaning the dataset and feature engineering;
• · Works together with the data engineer to create datasets in the necessary format for training multiple machine learning models;
• · Cleans, analyzes, organizes, integrates data, and helps in creating data pipelines;
• · Acts in exploratory and descriptive analyses, as well as predictive modeling, applying machine learning;
• · Applies continuous improvements to the models that make up the SISMOŴDEEPBLUE tool;
• · Analyzes and applies improvements to the data architecture, with direct communication with developers and/or Data Architects;
• · Leads oral and written presentations, as well as reports on results, for clients, partners, and other stakeholders;
• · Develops analysis reports, performance prediction, and predictive model development reports, directed at clients;
• · Uses PCA for possible experiments involving dimensionality reduction.
• · Uses notebooks like Jupyter and/or Google Colab;
• · Develops and improves AI models for analysis and forecasting of meteorological-oceanographic time series;
• · Applies data processing, quality, and validation techniques (e.g. QARTOD/NOAA);
• · Works together with oceanographers and engineers to interpret results;
• · Contributes to the evolution of our data analysis and visualization platform.