AI SW Infrastructure Engineer

Description Description As an AI SW Infrastructure Engineer, you will bridge the gap between research and production. Your primary responsibility will be to take machine learning models and algorithms developed by the Algorithms/Research teams and transform them into robust, optimized, and scalable components within Camtek’s production systems. You will focus on model optimization, software integration, and deployment, ensuring that AI solutions perform efficiently in real-world high-throughput environments. This role requires strong software engineering skills combined with a deep understanding of ML workflows and performance considerations. Key Responsibilities Integrate AI/ML models developed by research teams into production systems Optimize model performance for runtime, memory, and inference efficiency (e.g., TensorRT, ONNX) Adapt research-grade code into scalable, maintainable, and production-ready software Collaborate with Algorithms, Software, and System teams to ensure seamless end-to-end integration Improve inference pipelines and system performance in real-world environments Develop and maintain infrastructure for deploying and monitoring AI models in production Requirements Requirements B.Sc. in Computer Science, Electrical Engineering, or a related technical field from a recognized university 3+ years of hands-on experience in Machine Learning and software infrastructure development Strong programming skills in Python and experience with PyTorch Experience with software development in C++ or C# Experience working in Linux and Windows environments, including version control (Git) Strong understanding of multithreading and performance optimization Experience implementing and integrating algorithms into production systems Strong analytical and problem-solving skills Excellent collaboration, communication, and documentation skills Self-motivated, with the ability to work independently and drive tasks to completion Advantages Experience with computer vision pipelines and image data processing Hands-on experience with TensorRT and ONNX Familiarity with CUDA and GPU-level optimization Experience deploying ML models in production environments Familiarity with CI/CD pipelines Experience working with MLOps tools (e.g., MLflow, Kubeflow, or similar) Experience with generative models (e.g., diffusion models)