Join Optum, a global leader in healthcare technology, dedicated to improving health outcomes for millions worldwide. Our mission is to connect individuals with the care, pharmacy benefits, data, and resources they need to thrive. We foster an inclusive culture, offer opportunities to collaborate with talented peers, and provide comprehensive benefits and career development. Contribute to advancing health optimization on a global scale and make a tangible impact on the communities we serve.

This role is integral to our pursuit of Caring, Connecting, and Growing together.

Develop cutting-edge agentic workflows using Semantic Kernel, incorporating advanced features like tool calling, multi-agent coordination, and secure tool execution.

Build and optimize Retrieval Augmented Generation (RAG) pipelines, including chunking, embeddings, retrieval, and ranking, leveraging various vector stores such as Azure AI Search, Pinecone, Weaviate, and FAISS.

Ship resilient services using C# or Typescript, deployed with Docker and Kubernetes, ensuring robust CI/CD practices, observability, and efficient cost/latency management.

Deploy and manage Cloud Native solutions across Azure, AWS, and GCP. Integrate with enterprise systems through APIs, MCP servers, message buses, and event-driven architectures, designing appropriate function and tool schemas.

Implement Responsible AI practices, focusing on prompt injection defenses, content filters, PII/PHI redaction, audit logging, and human-in-the-loop mechanisms. Establish comprehensive offline and online LLM evaluations for accuracy, hallucination rates, and safety using frameworks like Ragas, DeepEval, and LangChain EvalGuide. Mentor junior developers to foster team growth.

A Bachelor's degree in Computer Science, Engineering, or a closely related field is required.

We seek a Senior AI/ML Engineer with over 8 years of professional experience, demonstrating strong proficiency in programming languages such as C#, Java, Python, or Go.

Key technical competencies include building agentic workflows with Semantic Kernel, implementing RAG pipelines with diverse vector stores, and developing robust services using C#/Typescript with containerization and CI/CD.

Experience with cloud platforms (Azure, AWS, GCP), enterprise system integration, and applying Responsible AI principles is essential. The ability to establish LLM evaluations and mentor junior engineers is also a critical requirement.