Lead Engineer, Automation and Application

Role Overview

• Lead the development, deployment, and production support of AI/ML-driven wafer-level and die-level image processing solutions for Automated Visual Inspection (AVI) tools used in front-end and back-end wafer fab operations.
• Design, implement, and sustain advanced vision and image processing pipelines, including Crack detection and advanced defect classification, Die-to-die and wafer-level image stitching, Optical inspection data analysis.
• Develop, train, validate, and maintain machine learning models used in AI-powered optical inspection, ensuring robustness, accuracy, and scalability in high-volume manufacturing environments.
• Integrate AI/ML-based solutions with fab automation systems, leveraging in-situ equipment and process data to enable anomaly prediction and early detection for critical processes.
• Work hands-on in the fab environment with automation team members, operations, process engineering, and equipment engineering teams to deploy, debug, and sustain automation, inspection, and process control solutions.
• Ensure reliable data foundations for inspection and process control applications, including data quality, traceability, and consistency across equipment, inspection, and analytics systems.
• Apply advanced analytics and machine learning techniques to improve inspection throughput and accuracy, process stability and yield, and root-cause identification.
• Support high-volume manufacturing operations by responding to production issues, minimizing downtime, and ensuring automation and inspection systems meet fab performance and reliability requirements.

Requirements

• Minimum 5 years' experience in data analytics in semiconductor, materials, or a related industry; or demonstratable equivalent abilities.
• BS/MS or equivalent degrees in computer science, software engineering, physics, mathematics, statistics or similar STEM field.
• Strong interpersonal, collaboration, and problem-solving skills, with the ability to work effectively in high-pressure manufacturing environments.
• Experience modeling, analyzing, and validating complex, imperfect real-world manufacturing and inspection datasets, including image and in-situ equipment data.
• Strong understanding of statistical fundamentals and their application to machine learning, defect detection, process monitoring, and anomaly identification.
• Solid knowledge of semiconductor manufacturing processes; background in process engineering, materials science, or related natural sciences is a plus.

Benefits

• Health insurance
• Professional development opportunities
• Equipment allowances
• Flexible working arrangements