Global Quality Intern, Data Science & Anomaly Detection

About our group:

The Global Quality AI/Process Control (AI/PC) team is focused on leveraging data science and machine learning to detect anomalies, improve predictive insights, and link upstream CTQs/KPIVs to reliability outcomes. We develop reproducible AI pipelines and scalable models that contribute directly to manufacturing and product reliability improvements.

About the role - you will:

• • Develop and test anomaly detection methods (z-score, IQR, clustering, ML-based outlier detection, time-series anomaly methods) for ORT/COH datasets.

  • Assist in benchmarking anomaly detection approaches against engineering rules (e.g., red/yellow dot sweeps, column swipes).

  • Build reproducible Python/KNIME pipelines for anomaly scoring, labeling, and classification at both head- and drive-level.

  • Partner with reliability engineers to link anomalies to upstream CTQs/KPIVs and propose early warning indicators.

  • Contribute to building MLOps-ready anomaly models that can scale across datasets (190k rows x 300+ columns per week).

What Will You Learn and Embark on at the Start

• You will start by learning Seagate's reliability and quality datasets, focusing on anomaly detection problems. Your early tasks will include prototyping statistical and machine learning-based anomaly detection methods, and working with SMEs to validate model outputs.

What You Would Ultimately Be Able to Be Proficient In

• You will develop advanced skills in anomaly detection, machine learning, and scalable data science workflows. You will gain hands-on experience with big data pipelines and MLOps practices while contributing to systematic AI deployment.

About you:

• Analytical, with strong problem-solving skills and curiosity to explore patterns in data.
• Adaptable and eager to learn advanced AI/ML methods.
• Collaborative team player with good communication skills.
• Able to work independently with large datasets.

Your experience includes:

• Currently pursuing a degree in Data Science, Statistics, Computer Engineering, or Applied Mathematics.
• Strong background in statistics and machine learning (regression, clustering, classification, anomaly detection).
• Proficiency in Python (pandas, scikit-learn, PyOD, statsmodels) or KNIME workflows.
• Understanding of time-series data analysis and anomaly scoring methods.

Location:

The Shugart site (named after Seagate's founder, Al Shugart) is a research and design center. Easily accessible from the One-North MRT Station, many employees choose to take mass transportation to work. Being a purpose-built building, The Shugart has excellent employee recreational facilities. Take an active break at our badminton courts, table tennis tables, in-house gym, and recreation rooms. Our yoga and Zumba classes are very popular. We also offer classes and interest groups in photography, gardening, and foreign languages, and have various on-site celebrations, and community volunteer opportunities

Location: Shugart, Singapore
Travel: None