Pablo Castillo

Computer Systems Engineer and Data Analyst with a solid understanding of Big Data and Machine Learning concepts. I thrive in collaborative team environments and prioritize effective communication. I actively support my colleagues and adopt a proactive approach to problem-solving. My passion for creative solutions motivates me to tackle complex challenges with enthusiasm. I am committed to continuous learning and knowledge sharing to foster mutual growth.

I developed a dynamic table digitization system for the product quality team, improving productivity by 30% through process optimization and enhanced accessibility. I collaborated closely with team members to gather requirements, ensuring the system's design met their needs. Working in an Agile environment using Scrum and Atlassian tools, I implemented an N-tier architecture for improved security and organization, while designing a user-friendly interface with React.js and Tailwind CSS.

I created an authentication module using ASP.NET Core API and migrated the database to Azure SQL Server. Additionally, I deployed the system on Azure App Services and provided ongoing support, ensuring smooth operation and user training.

During my studies in Computer Systems Engineering, I focused on the end-to-end development of systems by gathering requirements from stakeholders and turning them into comprehensive projects tailored to their needs. My technical skills were honed through hands-on experience with technologies such as .NET Core, SQL Server, Java, JavaScript, React.js, and tools like Postman, Git, Jira, and Bitbucket. This multidisciplinary background allowed me to approach system design, development, and deployment with a holistic understanding of both backend and frontend technologies.

In my Big Data minor, I gained expertise in data cleaning, exploratory data analysis (EDA), machine learning (ML), and data analytics. I applied these skills to a fraud analyzer project, where I developed predictive models to assess the likelihood of insurance fraud. Using R, I imported and cleaned data, applied imputation techniques, and utilized a variety of machine learning algorithms including KNN, Random Forest, SVM, and Neural Networks.

I compared the models using performance metrics to identify the most accurate one, which was then applied to a dataset with missing values for prediction. This project highlighted my ability to leverage advanced analytics and machine learning for practical business applications.