Job Description
Western Digital’s Big Data Technology & Industrial IoT team is seeking Masters-level interns passionate about applying Machine Learning, Deep Learning, and Optimization techniques to real-world problems in manufacturing, process control, and materials science. You will work on AI-driven models that enhance the reliability, yield, and sustainability of next-generation Hard Disk Drive (HDD) products — from materials characterization to factory optimization.
Key Responsibilities
- Design and implement predictive and optimization models for process yield, tool drift detection, and material performance using Deep Neural Networks, Gradient Boosting, or Graph Neural Networks.
- Apply Reinforcement Learning, Bayesian Optimization, or Evolutionary Algorithms to optimize process parameters, throughput, and energy consumption in high-volume manufacturing.
- Clean, preprocess, and augment large-scale sensor and experimental data. Interface with simulation tools (e.g., COMSOL, ANSYS) and integrate surrogate ML models for fast inference.
- Collaborate with data scientists, materials engineers, and process automation teams across global manufacturing sites to translate research into deployable solutions.
Qualifications
- Currently pursuing a Master’s degree in Machine Learning, Materials Science, Industrial Engineering, or related disciplines.
- Strong programming skills in Python, with experience in PyTorch, TensorFlow, Scikit-learn, Pandas, and Numpy.
- Knowledge of optimization algorithms, statistical modeling, and feature engineering.
- Exposure to time-series, image, or multi-modal data.
- Familiarity with Bayesian methods, Reinforcement Learning, or hybrid physics-informed ML is a plus.
- Strong analytical mindset with curiosity for bridging AI and physical sciences.
Learning Outcomes
- Experience in applying ML/DL to real industrial datasets and physical systems.
- Exposure to Digital Twin and Cognitive Factory frameworks for process optimization.
- Hands-on experience with cutting-edge ML infrastructure (GPU clusters, MLOps pipelines).
