The KLA Services team headquartered in Milpitas, CA is our service organization that consists of Service Sales and Marketing, Spares Supply Chain management, Field Operations, Engineering, Product Training, and Technical Support. The KLA Services organization partners with our field teams and customers in all business sectors to maintain the high performance and productivity of our products through a flexible portfolio of services. Our comprehensive services include: proactive management of tools to identify and improve performance; expertise in optics, image processing and motion control with worldwide service engineers, 24/7 technical support teams and knowledge management systems; and an extensive parts network to ensure worldwide availability of parts.
Job Description/Preferred Qualifications
Key Responsibilities
Design, train, and deploy computer vision models for object detection, classification, and positioning in semiconductor service environments
Build robust image and video processing pipelines that handle real-world field conditions
Develop and maintain training data pipelines: collection, annotation, augmentation, and quality assurance
Optimize models for inference performance across deployment targets — balancing accuracy, latency, and compute constraints
Integrate vision capabilities into broader multimodal AI systems that combine visual perception with knowledge retrieval and reasoning
Build evaluation frameworks that measure model performance against real field data
Design model architectures that serve both AI knowledge systems and future robotics/automation initiatives
Stay current with the vision model frontier and bring what's relevant into production
Document model architectures, training procedures, and deployment patterns so the team can build on your work
Qualifications
Bachelor's degree in Computer Science, Electrical Engineering, or related field; Master's preferred
1+ years of experience building and deploying computer vision systems (strong new grads with demonstrated projects or research considered)
Strong proficiency in Python and deep learning frameworks (PyTorch, TensorFlow)
Hands-on experience with object detection and classification architectures and transfer learning / fine-tuning approaches
Experience building training data pipelines — annotation tooling, data augmentation, and active learning strategies
Experience with model optimization techniques for edge or constrained deployment
Strong understanding of image processing fundamentals and camera systems
Self-directed — you experiment, iterate, and push boundaries without waiting for direction
Excellent problem-solving skills and ability to debug model failures in messy, real-world data
Prior experience in manufacturing, robotics, industrial inspection, or semiconductor environments is a plus
Experience with 3D vision, depth estimation, or point cloud processing is a plus
Minimum Qualifications
Master's Level Degree and 0 years related work experience; Bachelor's Level Degree and related work experience of 2 years