Machine Learning Engineer II, Infrastructure (머신러닝 엔지니어 II - 인프라)

Design, build, and maintain robust machine learning infrastructure to support large-scale ad serving and model training globally. Develop and optimize data pipelines and workflows for efficient model deployment and monitoring. Collaborate with data scientists, product managers, and software engineers to deliver end-to-end ML solutions. Implement best practices for model versioning, reproducibility, and CI/CD in ML systems. Build and operate high-performance ML systems using modern frameworks and languages such as JAX and Rust, optimized for execution on GPUs and TPUs. Monitor, troubleshoot, and continuously improve the reliability, scalability, and performance of ML systems delivering millions of predictions per second worldwide. Evaluate and integrate new tools, frameworks, and technologies to enhance the ML platform’s capabilities. Integrate AI-driven agents into the core engineering and modeling lifecycle to automate and amplify the team's impact. Contribute to the design and execution of experiments to improve ad quality and system performance. Document system architecture, processes, and best practices to ensure knowledge sharing and maintainability.