Design and deploy machine learning and big data solutions that integrate directly with Nokia’s manufacturing test platforms for coherent pluggable products.
Partner with test capability engineers to identify opportunities where predictive modeling, anomaly detection, and statistical inference can improve yield, reduce cycle time, and accelerate fault isolation.
Build and maintain scalable data pipelines that aggregate and normalize test data across manufacturing sites and product families.
Develop ML models for test outcome prediction, failure classification, and early warning of process drift or hardware degradation.
Apply unsupervised and supervised learning methods to identify latent patterns in optical transceiver test data.
Collaborate with cross-functional stakeholders — including development, manufacturing, and product engineering — to integrate ML insights into actionable test platform changes.
Establish and maintain best practices for model validation, versioning, and deployment within the test environment.
Communicate findings clearly to technical and non-technical audiences, including engineering leadership.

MS or PhD in Data Science, Machine Learning, Electrical Engineering, Computer Science, Applied Mathematics, Statistics, or a related quantitative field.
Strong foundation in machine learning methods: supervised/unsupervised learning, regression, classification, clustering, anomaly detection.
Proficiency in Python and data science stack (pandas, scikit-learn, PyTorch or TensorFlow, etc.).
Proficiency in SQL (MySQL or other relational database frameworks) for large-scale data extraction and analysis.
Experience with JMP or similar statistical analysis and visualization platforms.
Demonstrated ability to work with high-volume, real-world datasets in a production or research setting.
Strong data visualization and communication skills.

Machine Learning Test Capability Engineer

Key skills