• Build and maintain APIs, microservices, and middleware layers to serve ML and LLM models at scale, ensuring high availability and low latency • Implement validation, observability, and monitoring frameworks for data and ML systems to ensure reliability, traceability, and performance • Work closely with ML scientists to translate experimental models into production-grade systems, ensuring seamless integration with broader data and platform infrastructure • Continuously evaluate, refactor, and improve ETL and model serving pipelines for cost efficiency, speed, and reliability • Develop CI/CD pipelines for data workflows and model lifecycle management, including training, testing, deployment, and rollback • Share knowledge and mentor teammates on data engineering patterns, MLops practices, and scalable system design