Senior AI/ML Engineer - Machine learning, Agentic AI, LangGraph

Optum is a global organization that delivers care, aided by technology to help millions of people live healthier lives. The work you do with our team will directly improve health outcomes by connecting people with the care, pharmacy benefits, data and resources they need to feel their best. Here, you will find a culture guided by inclusion, talented peers, comprehensive benefits and career development opportunities. Come make an impact on the communities we serve as you help us advance health optimization on a global scale. Join us to start Caring. Connecting. Growing together.

GenAI Innovation & Technology Acceleration Lead the exploration, evaluation, and application of emerging GenAI technologies, with a strong focus on Agentic AI, conversational agents, autonomous workflows, multi-agent systems, and LLM-enabled enterprise automation Develop rapid prototypes, proof-of-concepts, technical accelerators, and reusable solution patterns that help accelerate AI adoption across business and technology teams Assess new AI frameworks, orchestration patterns, model capabilities, evaluation techniques, and deployment approaches to determine enterprise applicability, scalability, and risk Translate innovation concepts into practical engineering blueprints, reference implementations, and production-ready solutions Agentic AI Solution Design & Implementation Design and implement Agentic AI solutions using Python and modern AI orchestration frameworks such as LangChain, LangGraph, Semantic Kernel, AutoGen, CrewAI, ReACT, ReWOO, RAG, and agent-to-agent communication patterns Build intelligent agents capable of reasoning, planning, tool usage, memory management, API interaction, multi-step workflow execution, and context-aware conversational experiences Develop conversational AI systems that support multi-turn interactions, enterprise knowledge retrieval, user intent handling, task completion, personalization, and seamless integration with backend systems Implement RAG-based architectures using vector databases, embeddings, document processing pipelines, semantic search, reranking, grounding, and context optimization techniques Technical Engineering & Hands-On Delivery Contribute directly to software design, application development, prompt engineering, agent orchestration, evaluation pipelines, and production implementation Convert architectural guidance and innovation ideas into scalable, maintainable, secure, and well-tested engineering deliverables Develop APIs, microservices, reusable libraries, and platform components that enable GenAI capabilities to be integrated into enterprise applications Apply strong software engineering practices to ensure AI solutions are reliable, modular, extensible, observable, and production ready Cloud-Native AI Development Build and deploy secure, scalable, cloud-native AI solutions on Azure, using services such as Azure OpenAI, Azure AI Search, Azure Functions, Azure Kubernetes Service, Cosmos DB, Azure Container Apps, API Management, Key Vault, and related platform services Design solutions using microservices, event-driven architectures, serverless patterns, containerized workloads, and scalable cloud infrastructure Ensure AI solutions comply with enterprise standards for security, reliability, privacy, observability, resiliency, and operational excellence LLMOps, Evaluation & AI Reliability Develop evaluation frameworks for LLM and agentic systems, including response quality, factuality, hallucination risk, grounding accuracy, task completion rate, latency, cost, safety, and user experience Implement guardrails, safety checks, content filtering, fallback strategies, prompt versioning, model monitoring, and human-in-the-loop review mechanisms where appropriate Create automated testing and benchmarking approaches for prompts, agents, tools, workflows, RAG pipelines, and conversational experiences Continuously improve agent performance through experimentation, prompt