Principal AI Data Scientist – Wafer Fabrication

Coherent Corp. Vietnam•Fremont, CA

1d•$118,000 - $202,063•Hybrid

About The Position

Coherent is a global leader in lasers, engineered materials and networking components. We are a vertically integrated manufacturing company that develops innovative products for diversified applications in the industrial, optical communications, military, life sciences, semiconductor equipment, and consumer markets. Coherent provides a comprehensive career development platform within an environment that challenges employees to perform at their best, while rewarding excellence and hard-work through a competitive compensation program. It's an exciting opportunity to work for a company that offers stability, longevity and growth. Come Join Us! The Principal AI Data Scientist will analyze datasets generated by wafer fabrication processes, equipment, sensors, metrology systems, and manufacturing execution systems. They will apply statistical analysis, AI, machine learning, and data-mining techniques for deeper understanding of devices and fabrication processes, process monitoring and anomaly detection, wafer and lot excursion analysis, yield analysis and prediction, and root-cause investigation. The role involves collaborating with others using AI & ML, integrating data from multiple sources, and translating analytical results into clear engineering insights and actionable recommendations. The candidate will communicate findings to engineers and managers, work with engineers to distinguish correlation from causation, and develop reusable data pipelines, analytical tools, dashboards, and model-monitoring methods. Support for design of experiments, process characterization, and continuous improvement activities is also expected. Additionally, the role will help establish best practices for data quality, feature engineering, model validation, documentation, and responsible use of AI in development and manufacturing.

Requirements

A Bachelor’s degree in Data Science, Engineering, Science, Computer Science or Mathematics is required.
Minimum of 5 years of experience with AI, preferably including ML, preferably with experience in statistical analytic techniques.
Several years of professional experience applying machine learning, artificial intelligence, advanced statistics, and data science to real-world engineering or manufacturing problems.
Experience with SQL and modern data-processing or data-platform technologies.
Strong knowledge of statistical methods, experimental design, regression, classification, clustering, anomaly detection, and model evaluation.
Programming skills in Python and experience with common data-science and machine-learning libraries.
Experience in AI/ML model deployment through RESTful APIs, containerization, and container orchestration.
Experience working with structured, time-series, sensor, or high-volume manufacturing data.
Ability to work collaboratively with domain experts and explain complex analytical results in practical engineering terms.
Demonstrated ability to take an analysis from problem definition through deployment, validation, and communication of results.

Nice To Haves

A Master’s degree is preferred.
Experience with cloud-based ML training and inference using AWS, GCP, Azure, or Databricks is a plus.
Exposure to wafer fabrication, photonics, and telecommunications is a plus.

Responsibilities

Analyze datasets generated by wafer fabrication processes, equipment, sensors, metrology systems, and manufacturing execution systems.
Apply statistical analysis, AI, machine learning, and data-mining techniques for deeper understanding of devices and fabrication processes, process monitoring and anomaly detection, wafer and lot excursion analysis, yield analysis and prediction, and root-cause investigation.
Integrate data from multiple sources, including process recipes, equipment logs, sensor data, metrology results, defect inspection, and production history.
Translate analytical results into clear engineering insights and actionable recommendations.
Communicate these findings to engineers and managers.
Work with engineers to distinguish correlation from likely physical or process-driven causation.
Develop reusable data pipelines, analytical tools, dashboards, and model-monitoring methods.
Support design of experiments, process characterization, and continuous improvement activities.
Help establish best practices for data quality, feature engineering, model validation, documentation, and responsible use of AI in development and manufacturing.