Must have 3 years of experience in the following: 3 years of experience in design, development, and deployment of document understanding and processing pipelines; 3 years of experience in deploy, monitor, and maintain machine learning models (LLMs and agentic workflows) in a microservice environment using Docker, Kubernetes (AWS EKS), and internal platforms (ZCP); 3 years of experience in evaluating external data sources to enhance AI search/document understanding; 3 years of experience in developing performance metrics, monitoring systems, and optimizations for AI search pipelines to ensure scalability, efficiency, and low latency; 3 years of experience in design and maintaining data ingestion, preprocessing, and transformation pipelines for both structured and unstructured data, ensuring high data quality and reliability; 3 years of experience in architect and optimizing large-scale Machine Learning workflows to process structured and unstructured data for knowledge graphs and search services; 3 years of experience collaborating with cross-functional teams of engineers, product managers, and domain experts to define requirements and implement scalable, production-ready ML services; 3 years of experience optimizing knowledge graph algorithms for performance, scalability, and reliability. Conduct research on cutting-edge Machine Learning, NLP, and knowledge graph techniques, evaluating external data sources to enhance search and document understanding capabilities; Develop/maintain documentation, best practices, guidelines; Mentor junior engineers and contribute to team knowledge-sharing, best practices, and internal technical guidelines; Lead the design, development, and deployment of AI search pipelines, including document understanding and retrieval systems, using libraries such as Docling; Evaluate external data sources to enhance AI search/document understanding; Develop performance metrics, monitoring systems, and optimizations for AI search pipelines to ensure scalability, efficiency, and low latency; Develop and maintain AI-driven search and ranking algorithms for enterprise-scale information retrieval and RAG (Retrieval-Augmented Generation) systems; Design and maintain data ingestion, preprocessing, and transformation pipelines for both structured and unstructured data, ensuring high data quality and reliability.