Machine Learning Engineer
Core
Build and maintain model pipelines for anomaly detection and root cause analysis systems using large-scale manufacturing data.
Role type
Machine Learning Engineer (MLOps & Pipeline Engineering)
Builds
Scalable ML pipelines for semiconductor manufacturing data processing and model deployment
Domain
Semiconductor manufacturing / Industrial IoT
Deliverable
production ML models
Required skills
PySpark, Python ML libraries (scikit-learn, TensorFlow, PyTorch, XGBoost), MLOps practices, pipeline orchestration, model versioning, monitoring and alerting
Preferred skills
Model registry setup, automated retraining triggers, automated testing for pipelines and models, on-prem/private cloud cluster management
Technologies
PySpark, Python, scikit-learn, TensorFlow, PyTorch, XGBoost
Responsibilities
Build PySpark workflows to ingest and transform high-volume manufacturing data; Optimize Spark jobs for speed and memory efficiency; Design and maintain end-to-end ML pipelines for feature calculation, training, and deployment; Implement and tune machine learning models for anomaly detection and root cause analysis; Manage the model lifecycle including versioning, artifact storage, and rollback procedures; Monitor pipeline execution, data quality, and model metrics to detect failures or drift
Seniority
Mid-Senior, hands-on IC