AI ML Engineer

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.

We are looking for an AI/ML Engineer with strong expertise in Agentic AI to design and deploy LLM-powered solutions, multi-agent systems, and orchestration workflows. You'll work closely with product, engineering, and business teams to deliver scalable agentic AI solutions in production.

Primary Responsibilities:

• Design and deploy scalable Agentic AI solutions in production environments
• Develop LLM-powered solutions including RAG pipelines, agentic workflows, decisioning agents, and orchestration layers
• Work with agentic AI frameworks such as LangGraph and evaluation tools like DeepEval
• Design multi-agent orchestration patterns (orchestrator + subagent)
• Deploy and operate LLM-powered services at scale on cloud platforms (Azure / AWS / GCP)
• Contribute to MLOps practices, CI/CD pipelines, and automation
• Collaborate with product, engineering, and business teams to translate requirements into agentic AI solutions
• Stay updated with the latest advancements in Agentic AI and GenAI, and apply them to improve existing systems
• Review code and mentor junior engineers
• Comply with the terms and conditions of the employment contract, company policies and procedures, and any and all directives (such as, but not limited to, transfer and/or re-assignment to different work locations, change in teams and/or work shifts, policies in regards to flexibility of work benefits and/or work environment, alternative work arrangements, and other decisions that may arise due to the changing business environment). The Company may adopt, vary or rescind these policies and directives in its absolute discretion and without any limitation (implied or otherwise) on its ability to do so

What We Offer

• Opportunity to work on cutting-edge Agentic AI and GenAI systems
• Collaborative team environment with growth and learning opportunities
• Exposure to end-to-end AI product development

Required Qualifications:

• Bachelor's or Master's degree in Computer Science, Software Engineering, Data Science, or related field (or equivalent practical experience)
• 4+ years of hands-on experience delivering AI/ML solutions, with strong focus on LLMs, Generative AI, and Agentic AI
• Hands-on experience with LLM APIs (Azure OpenAI, Anthropic, Bedrock)
• Solid experience with agentic frameworks (LangGraph, CrewAI, AutoGen, or Agents SDK)
• Experience designing and implementing RAG architectures and working with GenAI frameworks
• Experience with vector databases (pgvector, Pinecone, Weaviate)
• Solid Git, pull request, and collaborative development workflow experience
• Familiarity with cloud platforms (Azure / AWS / GCP)
• Working knowledge of SQL, PostgreSQL, and Redis
• Solid proficiency in Python (FastAPI, Pydantic, async programming)
• Prompt engineering and structured outputs (JSON schema, function calling)
• Tool/function calling design and safety best practices
• Memory and context management (short-term and long-term)

Preferred Qualifications:

• Proven Skills:
  • Containerization and orchestration (Docker, Kubernetes)
  • Multi-agent orchestration (orchestrator plus subagent patterns)
  • Human-in-the-loop (HITL) review and approval workflows
  • LLM observability and evaluation tools (LangSmith, LangFuse, Ragas)
  • Responsible AI practices (PII redaction, prompt injection awareness)
  • Multi-tenant architecture and data isolation
  • Model Context Protocol (MCP) and agent-to-agent protocols
  • Experience with AI-assisted dev tools (GitHub Copilot, Cursor)
  • Workflow engines (Temporal, Airflow)
  • Knowledge graphs (Neo4j, GraphRAG)
  • Multimodal AI experience (vision, audio)
  • TypeScript / Node.js for full-stack agent UIs
  • Streaming UIs (SSE, WebSocket)
  • Cost optimization and model routing strategies
  • Message queues (Kafka, RabbitMQ)
  • Guardrails frameworks (NeMo Guardrails, Guardrails AI)
  • Enterprise integrations (Rally, GitHub, ServiceNow, SSO/OAuth)

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.