Analyze Ford's warranty claims data to identify defect trends in vehicle components/systems, common quality issues, and opportunities to reduce future warranty costs.
Mine voice of the customer data sources (surveys, social media, etc.) to surface top customer pain points around quality and product reliability.
Continuously improve the efficiency and accuracy of existing machine learning models.
Develop scalable model architectures for fast and reliable model retraining purposes.
Document and communicate findings and insights to stakeholders in a clear and concise manner.
Minimum Requirements:
Master’s degree in computer science, Statistics, Mathematics, Engineering, or a related quantitative field.
Minimum of two years of experience in Python programming language.
1+ years’ experience in SQL programming language and relational databases.
2+ years of experience with data analysis and visualization Python packages such as Pandas, SciPy, Seaborn, etc.
2+ years of experience with supervised machine learning algorithms and at least one of the following popular Machine learning frameworks: Scikit-learn, Pytorch, TensorFlow, and XGBoost.
Preferred Qualifications:
Ph.D. degree in Computer Science, Statistics, Mathematics, Engineering, or a related quantitative field is preferred.
Experience with Git and GitHub for version control and collaboration.
Experience with Google Cloud Platform for data processing and machine learning tasks.
Solid understanding of unsupervised machine learning algorithms such as isolation forests, one-class SVM, autoencoders, etc.
Familiarity with feature engineering concepts, Fourier transform, and statistical feature extraction and selection.
Excellent problem solving, communication, and data presentation skills.