Process Support Engineer Iii
Current• Trained supervised machine learning models to detect wafer defects with an accuracy rate of 95%, utilizing a labeled dataset of over 10,000 images for model training and validation.• Performed system stability evaluations under various operating conditions ensuring 90% uptime, minimizing production delays, and protecting sensitive photonic devices such as photomultiplier tubes.• Optimized tool performance by tuning optical inspection algorithms, increasing real defect detection and meeting customer process and integration requirements.