Job Description

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.

As a Lead AI/ML Engineer, you will play a key role in building and deploying production-grade Large Language Model (LLM) agents and Retrieval-Augmented Generation (RAG) pipelines that automate detection, triage, and remediation of platform and application issues.

Working at the intersection of machine learning engineering, system observability, and developer experience, you will design robust orchestration, guardrails, and evaluation frameworks to deliver high-impact AI capabilities.

You will partner closely with SRE, InfoSec, and platform teams to build scalable, secure, and responsible AI solutions integrated directly into existing software development workflows.

Primary Responsibilities:

• Design, develop, and deploy AI-powered solutions to address complex business challenges with an emphasis on responsible use of AI
• Build and deploy production LLM agents that automate detection, triage, and remediation of platform and application issues
• Design and tune RAG pipelines over runbooks, incident history, logs, code, and internal documentation, including chunking strategy, embedding selection, vector store design, hybrid/semantic search, and reranking
• Implement agent orchestration, including tool/function calling, multi-step planning, multi-agent handoffs, memory, and state management
• Build supporting infrastructure and software layers for agents, including tool wrappers, guardrails, human-in-the-loop approval paths, and fallback behavior
• Own model and prompt engineering, including model selection, prompt and context optimization, output structuring, cost/latency tuning, and fine-tuning or parameter-efficient techniques where warranted
• Build evaluation pipelines and define quality metrics for agent and RAG behavior (retrieval precision/recall, groundedness, hallucination/false-positive rate, escalation rate, MTTR impact) and iterate based on results
• Integrate agents with observability and security platforms (alerting, logging, metrics, vulnerability, and incident data) through APIs and Model Context Protocol (MCP) tool interfaces to deliver capabilities inside developer workflows
• Evaluate emerging AI trends and contribute reusable patterns, components, and documentation across the enterprise AI development lifecycle
• Use enterprise-approved AI tools to streamline workflows, automate tasks, and drive continuous improvement.
• Comply with all applicable Company policies, procedures, and business directives, changes including those relating to work location, team assignments, work schedules, and flexible work arrangements

Required Qualifications:

• Bachelor's degree or equivalent experience (e.g., 10+ years of software engineering or machine learning engineering experience in lieu of a degree)
• 10 + years of software engineering or machine learning engineering experience
• 10+ years of experience with proficiency in languages such as Java, C#, Python, or Go
• 6+ years of experience integrating third-party APIs and building backend services that run in production
• 6+ years of experience with cloud platforms (Azure, AWS, or GCP), containers, and CI/CD pipelines
• 2+ years of hands-on experience building with LLMs, including prompt engineering, tool/function calling, and agent or multi-step orchestration
• 2+ years of experience designing and shipping RAG systems in production, including embeddings, vector databases (e.g., Azure AI Search, Pinecone, Milvus, pgvector, or FAISS), and retrieval evaluation
• 2+ years of experience with Python, including working knowledge of agent frameworks (e.g., LangGraph, LangChain, LlamaIndex, Semantic Kernel, or CrewAI)
• 2+ years of experience building LLM evaluation and testing workflows rather than relying on manual spot checks

Preferred Qualifications:

• Experience with model fine-tuning or parameter-efficient fine-tuning (PEFT) techniques
• Experience integrating agents with enterprise observability and security platforms via APIs and MCP-style tool interfaces
• Proven ability to work across multidisciplinary teams (e.g., SRE, InfoSec, platform engineering) and translate operational pain points into technical requirements

At UnitedHealth Group, our mission is to help people live healthier lives and make the health system work better for everyone. We believe everyone - of every race, gender, sexuality, age, location and income - deserves the opportunity to live their healthiest life. Today, however, there are still far too many barriers to good health which are disproportionately experienced by people of color, historically marginalized groups and those with lower incomes. We are committed to mitigating our impact on the environment and enabling and delivering equitable care that addresses health disparities and improves health outcomes - an enterprise priority reflected in our mission.