Own reliability, security, scalability, and production operations for an agentic AI system on GCP. Manage Kubernetes and Cloud Run workloads, observability, SLOs, CI/CD, Terraform, identity, secrets, and supply-chain security. Build AI agents for incident triage and self-healing, address LLM security risks, and lead on-call incident response and postmortems.
Requisition Number: 2394629
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're looking for a Senior Agentic AI SRE to own the reliability, security and scalability of our agentic AI system on Google Cloud Platform (GCP). The role covers containers, identity and single sign-on (SSO), observability, CI/CD automation and production incident response. You'll also build AI agents that automate operations work.
Primary Responsibilities:
Required Qualifications:
Preferred Qualifications:
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.
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're looking for a Senior Agentic AI SRE to own the reliability, security and scalability of our agentic AI system on Google Cloud Platform (GCP). The role covers containers, identity and single sign-on (SSO), observability, CI/CD automation and production incident response. You'll also build AI agents that automate operations work.
Primary Responsibilities:
- Own the availability, performance and capacity of the agentic AI system on GCP, and define and track SLOs and error budgets
- Run containerized workloads on Kubernetes (GKE and Cloud Run), including scaling, resilience and cost optimization
- Build end-to-end observability (metrics, logs, traces, alerts), including AI-specific signals: token usage, model latency and agent failure rates
- Automate CI/CD pipelines and build management, including versioning, artifact management, safe rollouts and infrastructure as code (Terraform)
- Implement SSO (OAuth 2.0, OIDC, SAML), IAM, secrets management and container supply-chain security
- Address AI security risks such as prompt injection, data leakage and unsafe agent actions
- Build AI agents that automate incident triage, build failure analysis, runbooks and self-healing
- Take part in on-call and the production war room, lead incident response and run blameless postmortems
- 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 in Computer Science or equivalent experience
- 8+ years in SRE, DevOps or platform engineering, with 3+ years running production cloud systems
- Hands-on SSO and identity experience: OAuth 2.0, OIDC, SAML, Entra ID or Okta
- Solid hands-on GCP experience: GKE, Cloud Run, IAM, networking and Cloud Operations Suite
- Proven production incident and war room experience
- Knowledge of CI/CD tools (GitHub Actions, Cloud Build, Jenkins or Argo CD) and Terraform
- Knowledge of observability tools such as OpenTelemetry, Prometheus, Grafana, Cloud Monitoring or Splunk
- Working knowledge of LLM and agentic systems, such as Vertex AI/Gemini, RAG and agent frameworks
- Expertise with Docker and Kubernetes
- Solid Python and Bash skills
Preferred Qualifications:
- GCP or Kubernetes certifications: Professional Cloud DevOps Engineer, CKA or CKS
- Experience building AI agents for AIOps or ChatOps automation
- Experience with Model Context Protocol (MCP) or multi-agent orchestration
- Healthcare or other regulated-industry experience, including HIPAA
- Knowledge of LLM observability and evaluation tools such as LangSmith, Langfuse or Arize
- Knowledge of the OWASP Top 10 for LLM Applications
- Knowledge of policy as code (OPA) and supply-chain security (Binary Authorization, Sigstore)
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.
Similar Jobs at Optum
Artificial Intelligence • Big Data • Healthtech • Information Technology • Machine Learning • Software • Analytics
Leads the strategy, team, roadmap, and delivery of AI-powered automation for enterprise virtual workspace platforms. Develops solutions using generative AI, LLMs, machine learning, cloud services, APIs, infrastructure as code, and workflow orchestration. Partners with engineering, product, operations, vendors, and executives to improve productivity, service quality, cost efficiency, and user experience. Oversees operational analytics, responsible AI governance, talent development, budgets, and cross-functional technology programs.
Top Skills:
AWSAzureAzure Ai ServicesAzure Virtual DesktopCi/CdCitrixDatabricksDevOpsGitInfrastructure As CodeKafkaLarge Language ModelsMachine LearningMicrosoft CopilotPowershellPythonRest ApisSnowflakeVmware Horizon
Artificial Intelligence • Big Data • Healthtech • Information Technology • Machine Learning • Software • Analytics
Manage physician billing accounts receivable by reviewing outstanding insurance balances, coordinating with payers and clients, analyzing EOBs and denials, resolving claim payment issues, and identifying trends that improve denial rates and reduce AR aging. The role requires knowledge of the revenue cycle, medical insurance plans, HIPAA, denial management, CMS-1500 claims, Microsoft Office, and effective communication with internal and external stakeholders.
Top Skills:
Cms-1500 Claim FormHipaaExcelMS OfficeMicrosoft Outlook
Artificial Intelligence • Big Data • Healthtech • Information Technology • Machine Learning • Software • Analytics
Develop and execute quality strategies for agentic AI systems, including manual testing, automated evaluation, API and end-to-end testing, safety and security validation, production monitoring, and CI/CD quality gates. Build frameworks for prompts, model outputs, retrieval, tool calls, and multi-step workflows. Investigate failures, detect quality regressions and drift, publish dashboards, and partner with engineering, product, and SRE teams on corrective actions.
Top Skills:
APIsArizeAWSAzureBrowserstackCi/CdDeepevalDynatraceGCPGeminiHipaaJavaJavaScriptJmeterLangfuseLangsmithLlmsLoadrunnerMcpOpentelemetryOwasp Top 10 For Llm ApplicationsPlaywrightPytestPythonRagRagasSauce LabsSeleniumSonarqubeSql DatabasesTypescriptVertex Ai
What you need to know about the Kolkata Tech Scene
When considering the industries shaping India's tech scene, gaming might not immediately come to mind. However, in the last decade, increased internet usage and greater access to mobile devices have catapulted the industry to new heights, with Kolkata-based companies like Virtualinfocom, Red Apple Technologies and Digitoonz, at the forefront, driving the design and animation of new gaming titles for players.
