Alejandro Aguirre Alvarez

Senior Associate.

• Data Science and Analytics: Designed and implemented data lakes, conducted data analysis, and developed machine learning algorithms and NLP solutions within big data contexts.
• Proficient in Python Backend Development: Developed robust Python backend for scalable ML applications focused on microservices architecture.
• Cloud Technologies User: Built and managed microservices in Google Cloud Platform (GCP); experienced with AWS data pipelines and cloud computing platforms (S3, EC2, Redshift, Glue, GCP Cloud Run, Cloud Build).
• Product Management: Managed end-to-end product development and strategy, aligning with new market ventures.
• Project Leadership: Led projects to automate decision-making processes using Pyspark, NLP, probabilistic matching algorithms, and recursive queries.

Manufacturing Materials Flow Data Scientist.

Role Overview: Spearheaded data-driven initiatives as a Manufacturing Materials Flow Data Scientist, leveraging advanced machine learning models to optimize manufacturing decision-making processes, enhance production efficiency, and reduce operational costs in the aerospace sector.

Key Achievements:

• Smart Manufacturing: Designed and implemented a predictive analytics framework using Python, integrating IoT data with machine learning algorithms to predict manufacturing process failures, minimizing production backlog 34%, and reduce overtime 17%.
• Production Leveling: Innovated a machine learning-driven classification system for manufacturing parts to optimize production flows. This initiative streamlined the assembly process, and significantly enhanced overall manufacturing agility and efficiency.
• Technologies & Methodologies Used: Python, IoT, Logistic Regression, k-Means, Random Forest, Cluster-Based-Oversampling-SMOTE

Role Overview:
Led the Digital Transformation of Tooling's Department at a national scale. The project aimed at transforming the department's data management processes. The goal was to migrate from a disparate system of spreadsheets, standalone applications, ERP systems, and VBA macros to a streamlined, semi-automated data centralization and analytics dashboard. This initiative was designed to enhance operational efficiency, improve data accuracy, and provide actionable insights through advanced analytics.

Key Achievements:

• Data Dictionary Development: Crafted a detailed data schema for various tooling fabrication operations, ensuring fine granularity and comprehensive data representation.
• Data Collection Enhancement: Implemented a robust data collection framework, using statistical methods to validate sampling sizes (N) and identifying critical data sources within SAP and other isolated systems. This phase linked manufacturing production data directly to the tooling department, setting a solid foundation for accurate analytics.
• ETL Pipeline Construction: Developed a local-based ETL pipeline using Python and SQL to centralize disparate data sources, significantly improving data accessibility and integrity.
• Machine Learning Data Curation: Performed advanced data curation, establishing a statistically validated mean metric for operational processing times and standardizing data for machine learning readiness.
• Machine Learning Model Development: Built a Multiple Linear Regression (MLR) model to accurately predict processing times for mass-customization in the department, enhancing predictive capabilities and operational planning.
• Analytics Dashboard Design: Designed and implemented a Streamlit-Based analytics dashboard featuring key metrics, dynamic plots, and a Just-In-Time (JIT) job scheduler to facilitate real-time decision-making and operational monitoring.
• Web Application Deployment: Hosted the app on a local server, providing user-friendly access to the dashboard and predictive processing time functionalities, further democratizing data access and utility within the department.