About the role
The Machine Learning Ops (MLOps) Engineer will build and scale machine learning operations to support semiconductor manufacturing processes. This role focuses on deploying models for yield optimization and defect detection while maintaining robust CI/CD pipelines to bridge the gap between data science and factory production.
BankingOnsite
Key Responsibilities
- Build and maintain scalable ML pipelines for semiconductor yield analysis and defect detection systems
- Implement automated model deployment and monitoring infrastructure using Kubernetes and Docker
- Develop CI/CD workflows to streamline the transition of models from research to production
- Collaborate with data scientists to optimize model performance and resource utilization
- Ensure data integrity and versioning for high-volume manufacturing datasets
- Integrate ML services with factory automation systems and Manufacturing Execution Systems (MES)
- Troubleshoot and resolve production issues related to model inference and infrastructure
Requirements
- Bachelor's or Master's degree in Computer Science, Data Science, or a related engineering field
- Proven experience in MLOps or DevOps within a high-tech manufacturing or hardware environment
- Strong programming skills in Python and familiarity with C++ or Java
- Expertise in containerization and orchestration using Docker and Kubernetes
- Hands-on experience with ML frameworks such as PyTorch, TensorFlow, or Scikit-learn
- Experience with automation tools like Jenkins, GitLab CI, or GitHub Actions
- Familiarity with cloud-based ML services such as AWS SageMaker or Google Vertex AI
- Knowledge of model monitoring and observability tools
- Ability to work effectively in cross-functional teams involving both software and hardware engineers