Gabriel Sanders

- Led the implementation of an AI-powered invoice-review automation, cutting manual effort, preventing revenue leakage, and clearing a backlog that would have caused major payment delays. - Developed an end-to-end data platform, combining Apache Airflow orchestration with a custom-built UI to centralize distributed warehouse/carriers data into a structured database, providing field teams with a unified and intuitive hub for rapid decision-making. - Engineered automated reporting systems with multi-channel delivery (WhatsApp and Email), enhancing communication efficiency and providing stakeholders with seamless access to critical insights. - Utilized AI-augmented development (Cursor) to accelerate the delivery of interactive monitoring tools within a proprietary internal application, using JavaScript to visualize complex data pipelines and operational metrics in real-time.

- Built an automated data pipeline using Python, Pandas, and Excel to clean, unify, aggregate, and upload more than a thousand repair orders from about 100 different dealers on a weekly basis. - Developed data-driven insights using Power BI, Pandas, Matplotlib, and Excel in the form of BI dashboards and graphs, based on collaboration with eight different departments and an understanding of their needs. - Communicate primarily in English, enhancing professional and technical discussions.

- Led the administration and coordination of the autonomous systems division, overseeing the development of an autonomous system for a student-built formula car. - Managed interdepartmental communication and supported a multidisciplinary team, ensuring seamless collaboration across the mechanical, electrical, and computer engineering departments. - Managed relationships with external stakeholders, including companies and sponsors, ensuring alignment with organizational goals and securing necessary resources. - Together with the Techincal Directior, guided the development of the autonomous systems, identifying improvements and driving innovation throughout the process.

Computer vision applications, leveraging advanced object detection and localization techniques. - Utilized YOLO (You Only Look Once) for real-time object detection, ensuring high accuracy and speed in identifying objects within a scene. - Combined YOLO with depth mapping techniques to accurately determine the spatial position of objects relative to the camera, enabling precise 3D positioning. Applied this integrated approach in an autonomous student formula car system.

Utilized LIDAR (Light Detection and Ranging) sensor technology to capture and analyze spatial data for various applications. - Implemented RANSAC (Random Sample Consensing Techniquesus) for noise filtering and outlier detection, enhancing the precision of spatial data. - Applied DBSCAN (Density-Based Spatial Clustering of Applications with Noise) for effective clustering and pattern recognition, enabling better insights in complex datasets. Contributed to projects in mapping and autonomous navigation, using optimized LIDAR data to improve performance and reliability in real-world applications.