Architected and deployed an automated machine vision pipeline utilizing Python, PostgreSQL, Docker, and AWS, reducing R&D workload by over 40 percent.Championed the standardization and organization of code and documentation, significantly expediting software and ML development and facilitating the collection and preservation of institutional knowledge.Implemented a data engineering and ML pipeline for streamlined and iterative model development, producing predictive models that met or exceeded known benchmarks.

Led a comprehensive evaluation of commercial Electronic Lab Notebook products, culminating in the unanimous selection of an optimal solution that aligned with key stakeholder requirements.Architected and developed a proof-of-concept ML-driven web application using Flask, Tensorflow, Pytorch, AWS, and Docker to validate strategic business models and identify critical areas for enhancement.Conducted interactive demonstrations of data capture and ML proof-of-concepts, effectively showcasing operational enhancements and value to non-technical stakeholders.

Led the integration and testing of a Scientific Data Management System (SDMS), successfully automating data collection across more than 30 types of lab instruments.Developed Electronic Lab Notebook templates to streamline structured R&D data capture, and created data pipelines and dashboards using SQL, Python and Tableau, for enhanced experimental and inventory analytics.Administered the organization’s scientific data systems, overseeing robust change management processes that ensured seamless operations and minimal disruption to ongoing scientific research.