• Build and maintain scalable systems and infrastructure for deploying and serving ML models. • Design low-latency, fault-tolerant model inference systems using Amazon SageMaker. • Implement safe deployment strategies like blue/green deployments and rollbacks. • Create and manage CI/CD pipelines for ML workflows. • Monitor model performance and system health using AWS observability tools (e.g., CloudWatch). • Develop internal tools and APIs to help ML teams deploy and monitor models easily. • Collaborate with ML engineers, data scientists, and DevOps to productionize new models. • Participate in code reviews, system design, and platform roadmap discussions. • Continuously improve deployment reliability, speed, and usability of the ML platform.