Join Optum, a global leader in health optimization, and contribute to improving health outcomes worldwide. We leverage technology to connect individuals with essential care, pharmacy benefits, data, and resources.

Our inclusive culture fosters collaboration with talented peers, offers comprehensive benefits, and provides abundant career development opportunities. Be part of a team that is making a significant impact on communities by advancing global health.

We are seeking a skilled AI or ML Engineer to drive innovation in healthcare technology and help millions live healthier lives.

Design and implement advanced multi-agent AI systems utilizing LangChain, LangGraph, and MCP, incorporating sophisticated memory architectures. Build robust Retrieval-Augmented Generation (RAG) pipelines, covering text chunking, embedding, indexing, and vector retrieval. Develop and manage AI agent orchestration frameworks, ensuring reliable tool integration, memory updates, and seamless agent-to-agent communication. Integrate Large Language Models (LLMs) with enterprise systems via secure APIs, employing prompt orchestration and contextual memory. Implement and optimize vector database solutions for efficient data management. Architect and deploy production-ready AI pipelines on Azure, leveraging Azure AI Foundry for model hosting and evaluation, Azure AI Search for advanced retrieval, and Azure Container Apps/AKS for scalable deployment. Containerize and deploy AI systems using Docker and Azure Container Registry, orchestrating with ACA/AKS. Ensure production-ready agentic/RAG solutions with CI/CD, observability, autoscaling, and reliability best practices. Collaborate closely with product and data engineering teams to deliver comprehensive AI capabilities. Adhere to all company policies and directives, including those related to work location, team assignments, schedules, and flexible work arrangements.

A graduate or postgraduate degree in Computer Science, Engineering, Science, or a related field is required (e.g., B.Tech., MCA, Graduation with 15+ years of formal education; correspondence courses are not considered). Possess a minimum of 6 years of total professional experience. Demonstrate hands-on expertise with LangChain, LangGraph, and MCP (Model Context Protocol). Exhibit extensive experience with RAG architecture, including Vector storage and retrieval, Embedding pipelines, and Query routing and relevance tuning. Have practical knowledge of vector databases and similarity search algorithms. Show a solid understanding of AI concepts, such as multi-agent systems, Memory architectures, and Reasoning & tool-driven agents. Proficiency in Python, relevant AI/ML libraries, and API development is essential.