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.
Primary Responsibilities:
- Design and implement multi-agent AI systems using LangChain, LangGraph, MCP, and advanced memory architectures
- Build Retrieval-Augmented Generation (RAG) pipelines including text chunking, embedding, indexing, and vector retrieval
- Develop and maintain AI agent orchestration frameworks, ensuring reliable tool use, memory updates, and agent to agent communication
- Integrate LLMs with enterprise systems through secure API patterns, prompt orchestration, and contextual memory
- Implement and optimize vector database solutions
- Architect production-reference AI pipelines on Azure using:
- Azure Foundry (Azure AI Foundry) for model hosting, evaluation, and monitoring
- Azure AI Search for hybrid retrieval, semantic search, and grounding
- Azure Container Apps / Azure Kubernetes Service (AKS) for scalable deployment
- Containerize and deploy AI systems using Docker, Azure Container Registry (ACR), and orchestrate using ACA/AKS
- Productionize agentic/RAG solutions with CI/CD, observability, autoscaling, and reliability best practices
- Collaborate with product and data engineering teams to deliver end-to-end AI capabilities
- 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:
- Graduate or Postgraduate in Computer Science /Engineering/Science or related field, B.Tech./MCA/Graduation (15+ years of formal education, Correspondence courses are not relevant) 6+ years of total experience
- Hands-on expertise with: Lang Chain, Lang Graph and MCP (Model Context Protocol)
- Experience with RAG architecture, including Vector storage and retrieval, Embedding pipelines, Query routing and relevance tuning
- Practical knowledge of vector databases and similarity search
- Solid understanding of AI concepts, including multi-agent systems, Memory architectures, Reasoning & tool driven agents
- Proficient in Python, AI/ML libraries, and API development
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.
Skills Required
- Graduate, postgraduate, B.Tech., MCA, or equivalent degree in Computer Science, Engineering, Science, or a related field, with 15+ years of formal education
- 6+ years of total professional experience
- Hands-on expertise with LangChain, LangGraph, and MCP
- Experience with RAG architecture, vector storage and retrieval, embedding pipelines, query routing, and relevance tuning
- Practical knowledge of vector databases and similarity search
- Understanding of multi-agent systems, memory architectures, reasoning, and tool-driven agents
- Proficiency in Python, AI/ML libraries, and API development
Optum Compensation & Benefits Highlights
-
Leave & Time Off Breadth — Paid time off is often regarded as generous, with meaningful accrual and flexibility to use it. While practices can vary by team, the overall time-off offering stands out as a relative strength.
-
Retirement Support — A 401(k) plan with employer matching is available and generally well-regarded for supporting long-term savings. It remains valuable, though candidates should verify the current match formula.
-
Parental & Family Support — Programs such as parental leave, family medical leave, and adoption assistance are included as notable elements of the total rewards package. These resources can meaningfully support work-life balance when applicable to the role and location.
Optum Insights
What We Do
Optum, part of the UnitedHealth Group family of businesses, 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. At Optum, we support your well-being with an understanding team, extensive benefits and rewarding opportunities. By joining us, you’ll have the resources to drive system transformation while we help you take care of your future. We recognize the power of connection to drive change, improve efficiency and make a difference in health care. Join a team where your skills and ideas can make an impact and where collaboration is key to creating technology that produces healthier outcomes.
Gallery
.jpg)
Optum Offices
Hybrid Workspace
Employees engage in a combination of remote and on-site work.
Optum has three workplace models that balance the needs of the business and the responsibilities of each role. These models, core on‑site (5 days/week), hybrid (4 days/week) and telecommute or fully remote, vary by country, role and location.
