At GE Aerospace, I contribute to an AWS-hosted AI assistant serving 100+ users, using Python, Docker, and SQL to surface insights from enterprise documentation.
I also develop machine-learning model functions for probabilistic optimization and cost prediction, and review code on GitHub. As a Lean focal, I mentor new team members and contribute to knowledge sharing and process improvement.
Previously at GE Aerospace, I developed a Python cost-estimation tool that automated cost updates and reduced turnaround time by 60%. I also enhanced legacy applications, automated testing, and supported CI/CD workflows using Jenkins.
At NewSpace Research and Technologies, I developed a machine-learning model for BLDC motor efficiency prediction that reduced prediction error from 20% to 4%. I also worked on UAV propulsion systems, design optimization, CAD models, and propulsion validation.

