Principal Infrastructure & Reliability Engineer

{
  "content_hash": "5b1414847ad38a46fa9fb12ab64caaa25bd4a14743c87dc5a7ea3b7ced1edca9",
  "source_hash": "a25044617e0d421207826c3a434adf38fc99ecc7d52b4833298b276f20876c53",
  "last_changed_at": "2026-06-06T11:29:46.257Z",
  "active_status": "active"
}

{
  "language": "en",
  "location": {
    "raw": "United States",
    "city": null,
    "region": null,
    "country": "United States",
    "is_remote": false,
    "confidence": 0.8
  },
  "salary_max": 199500,
  "salary_min": 86400,
  "inferred_at": "2026-06-06T11:29:44.338Z",
  "launch_scope": {
    "reason": "english_us_canada",
    "included": true,
    "language": "en",
    "location": {
      "raw": "United States",
      "city": null,
      "region": null,
      "country": "United States",
      "is_remote": false,
      "confidence": 0.8
    },
    "countries": [
      "United States"
    ]
  },
  "remote_policy": "hybrid",
  "salary_period": "year",
  "workplace_type": "hybrid",
  "salary_currency": "USD"
}

{}

{
  "detail": {
    "Id": "328742",
    "Title": "Principal Infrastructure & Reliability Engineer",
    "media": [],
    "skills": [],
    "JobType": null,
    "Category": "Product Development",
    "JobGrade": null,
    "JobLevel": null,
    "JobShift": null,
    "WorkDays": null,
    "WorkHours": null,
    "WorkYears": null,
    "Department": null,
    "HotJobFlag": false,
    "StudyLevel": null,
    "WorkMonths": null,
    "WorkerType": null,
    "GeographyId": 300000000149325,
    "JobFamilyId": 300000001917356,
    "JobFunction": "PRODEV-ENGSVCS",
    "JobSchedule": "Full time",
    "BusinessUnit": null,
    "ContractType": null,
    "Organization": null,
    "TrendingFlag": false,
    "workLocation": [],
    "ContentLocale": "en",
    "HiringManager": null,
    "LegalEmployer": null,
    "RequisitionId": 302963406309455,
    "WorkplaceType": "",
    "BusinessUnitId": 300001096431127,
    "OrganizationId": 300001902541887,
    "GeographyNodeId": 100257187667965,
    "JobFunctionCode": "PRODEV-ENGSVCS",
    "LegalEmployerId": 300000000482027,
    "PrimaryLocation": "United States",
    "RequisitionType": "Professional",
    "NumberOfOpenings": null,
    "WorkplaceTypeCode": null,
    "BeFirstToApplyFlag": false,
    "otherWorkLocations": [],
    "secondaryLocations": [],
    "ExternalContactName": null,
    "ShortDescriptionStr": "Join Oracle's Health Data Intelligence (HDI) team as a Software Engineer 4, focused on Site Reliability Engineering for large-scale healthcare analytics platforms. In this role, you will design, build, and operate highly reliable, scalable infrastructure and data pipelines that power mission-critical analytics globally.\nYou will also contribute to the next evolution of cloud operations by advancing automation, observability, and AI-assisted reliability practices. This includes exploring the use of Generative AI and intelligent automation to improve incident response, system resilience, and operational efficiency.\nYou will work within a collaborative team to deliver robust solutions that handle massive datasets with precision and performance, while continuously improving system reliability and operational excellence.",
    "ExternalContactEmail": null,
    "ExternalPostedEndDate": null,
    "OtherRequisitionTitle": null,
    "requisitionFlexFields": [
      {
        "Value": "Individual Contributor",
        "Prompt": "Role",
        "ControlType": "SingleChoiceList",
        "SequenceNumber": 4
      },
      {
        "Value": "Regular Employee",
        "Prompt": "Job Type",
        "ControlType": "SingleChoiceList",
        "SequenceNumber": 5
      },
      {
        "Value": "Yes",
        "Prompt": "Does this position require a security clearance?",
        "ControlType": "SingleChoiceList",
        "SequenceNumber": 12
      },
      {
        "Value": "3 to 5+ years",
        "Prompt": "Years",
        "ControlType": "SingleChoiceList",
        "SequenceNumber": 13
      },
      {
        "Value": "Visa / work permit sponsorship is not available for this position",
        "Prompt": "Additional Info",
        "ControlType": "SingleChoiceList",
        "SequenceNumber": 45
      },
      {
        "Value": "English",
        "Prompt": "Applicants are required to read, write, and speak the following languages",
        "ControlType": "TextArea",
        "SequenceNumber": 46
      }
    ],
    "ApplyWhenNotPostedFlag": true,
    "DomesticTravelRequired": null,
    "ExternalDescriptionStr": "<p style=\"margin-bottom: 12pt\">Join Oracle's Health Data Intelligence (HDI) team as a Software Engineer 4, focused on Site Reliability Engineering for large-scale healthcare analytics platforms. In this role, you will design, build, and operate highly reliable, scalable infrastructure and data pipelines that power mission-critical analytics globally.<br>\n  You will also contribute to the next evolution of cloud operations by advancing automation, observability, and AI-assisted reliability practices. This includes exploring the use of Generative AI and intelligent automation to improve incident response, system resilience, and operational efficiency.<br>\n  You will work within a collaborative team to deliver robust solutions that handle massive datasets with precision and performance, while continuously improving system reliability and operational excellence.<br><br><i><span><strong>U.S. citizenship is required for this position, as the successful candidate will be required to obtain (and maintain) a U.S. government security clearance after hire.</strong></span></i></p>\n<p><span><strong>Required Skills</strong></span></p>\n<p><span><strong>Infrastructure &amp; Reliability</strong></span></p>\n<ul style=\"list-style-type: disc\">\n <li><span>Experience building and operating high-availability, fault-tolerant systems</span></li>\n <li><span>Strong understanding of distributed systems, performance monitoring, and resiliency patterns</span></li>\n <li><span>Experience with incident response, root-cause analysis, and production troubleshooting</span></li>\n</ul>\n<p>&nbsp;</p>\n<p><span><strong>AI-Native Engineering (NEW)</strong></span></p>\n<ul style=\"list-style-type: disc\">\n <li><span>Hands-on experience applying Generative AI or Agentic AI (e.g., LangChain, AutoGPT, custom agents) to:&nbsp;</span>\n  <ul style=\"list-style-type: circle\">\n   <li><span>Infrastructure lifecycle management&nbsp;</span></li>\n   <li><span>Observability and anomaly detection&nbsp;</span></li>\n   <li><span>Incident response and remediation automation&nbsp;</span></li>\n  </ul></li>\n <li><span>Ability to design or integrate AI-driven workflows for operational efficiency and reliability&nbsp;</span></li>\n <li><span>Familiarity with building or integrating autonomous agents for DevOps/SRE use cases</span></li>\n</ul>\n<p>&nbsp;</p>\n<p><span><strong>Cloud &amp; Multi-Cloud Ecosystems</strong></span></p>\n<ul style=\"list-style-type: disc\">\n <li><span>Strong experience with <strong>multi-cloud environments</strong> (OCI, AWS/Azure)&nbsp;</span></li>\n <li><span>Deep understanding of cloud infrastructure design, deployment, and resource optimization&nbsp;</span></li>\n <li><span>Experience managing hybrid or cross-cloud architectures&nbsp;</span></li>\n</ul>\n<p>&nbsp;</p>\n<p><span><strong>DevOps/SRE Practices</strong></span></p>\n<ul style=\"list-style-type: disc\">\n <li><span>Advanced competency in CI/CD pipelines (Jenkins, Kubernetes)&nbsp;</span></li>\n <li><span>Infrastructure as Code (Terraform)&nbsp;</span></li>\n <li><span>Observability tools (Prometheus, Grafana)&nbsp;</span></li>\n <li><span>Strong focus on <strong>automation-first operations</strong></span></li>\n</ul>\n<p>&nbsp;</p>\n<p><span><strong>Data Technologies</strong></span></p>\n<ul style=\"list-style-type: disc\">\n <li><span>Proficiency in Data Warehousing platforms (e.g., Vertica, Snowflake)&nbsp;</span></li>\n <li><span>Experience with ETL frameworks and large-scale data processing&nbsp;</span></li>\n <li>\n  <p><span>Understanding of columnar storage systems&nbsp;</span></p>\n  <p>&nbsp;</p></li>\n</ul>\n<p>&nbsp;</p>\n<p><span><strong>BI &amp; Reporting</strong></span></p>\n<ul style=\"list-style-type: disc\">\n <li>\n  <p><span>Experience supporting or integrating BI tools (Tableau, Power BI, Oracle Analytics)&nbsp;</span></p>\n  <p>&nbsp;</p>\n  <p>&nbsp;</p></li>\n</ul>\n<p><span><strong>Programming &amp; Tools</strong></span></p>\n<ul style=\"list-style-type: disc\">\n <li><span>Strong proficiency in Python, Java, or Go&nbsp;</span></li>\n <li><span>Experience with Docker, Kubernetes, and shell scripting&nbsp;</span></li>\n</ul>\n<p>&nbsp;</p>\n<p><span><strong>Problem-Solving</strong></span></p>\n<ul style=\"list-style-type: disc\">\n <li><span>Strong troubleshooting skills with ability to perform root-cause analysis&nbsp;</span></li>\n <li><span>Experience resolving complex production issues in distributed systems&nbsp;</span><br><br>\n   &nbsp;</li>\n</ul>",
    "ObjectVerNumberProfile": "1",
    "PrimaryLocationCountry": "US",
    "CorporateDescriptionStr": "<p style=\"margin-bottom:12pt\">Only Oracle brings together the data, infrastructure, applications, and expertise to power everything from industry innovations to life-saving care. And with AI embedded across our products and services, we help customers turn that promise into a better future for all. Discover your potential at a company leading the way in AI and cloud solutions that impact billions of lives.</p>\n<p style=\"margin-bottom:12pt\">True innovation starts when everyone is empowered to contribute. That’s why we’re committed to growing a workforce that promotes opportunities for all with competitive benefits that support our people with flexible medical, life insurance, and retirement options. We also encourage employees to give back to their communities through our volunteer programs.</p>\n<p style=\"margin-bottom:12pt\">We’re committed to including people with disabilities at all stages of the employment process. If you require accessibility assistance or accommodation for a disability at any point, let us know by emailing <u><a href=\"mailto:[email protected]\" target=\"_blank\" rel=\"nofollow\">[email protected]</a></u> or by calling 1-888-404-2494 in the United States.</p>\n<p style=\"margin-bottom:12pt\">Oracle is an Equal Employment Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, sexual orientation, gender identity, disability and protected veterans’ status, or any other characteristic protected by law. Oracle will consider for employment qualified applicants with arrest and conviction records pursuant to applicable law.</p>",
    "ExternalPostedStartDate": "2026-06-05T19:00:07+00:00",
    "ExternalQualificationsStr": "Disclaimer:<br><br><b>Certain US customer or client-facing roles may be required to comply with applicable requirements, such as immunization and occupational health mandates.</b><br><br><b>Range and benefit information provided in this posting are specific to the stated locations only</b><br><br>US: Hiring Range in USD from: $86,400 to $199,500 per annum. May be eligible for bonus and equity.<br><br>Oracle maintains broad salary ranges for its roles in order to account for variations in knowledge, skills, experience, market conditions and locations, as well as reflect Oracle's differing products, industries and lines of business.<br>Candidates are typically placed into the range based on the preceding factors as well as internal peer equity.<br><br>Oracle US offers a comprehensive benefits package which includes the following:<br>1.   Medical, dental, and vision insurance, including expert medical opinion<br>2.   Short term disability and long term disability<br>3.   Life insurance and AD&D<br>4.   Supplemental life insurance (Employee/Spouse/Child)<br>5.   Health care and dependent care Flexible Spending Accounts<br>6.   Pre-tax commuter and parking benefits<br>7.   401(k) Savings and Investment Plan with company match<br>8.   Paid time off: Flexible Vacation is provided to all eligible employees assigned to a salaried (non-overtime eligible) position. Accrued Vacation is provided to all other employees eligible for vacation benefits. For employees working at least 35 hours per week, the vacation accrual rate is 13 days annually for the first three years of employment and 18 days annually for subsequent years of employment. Vacation accrual is prorated for employees working between 20 and 34 hours per week. Employees working fewer than 20 hours per week are not eligible for vacation.<br>9.   11 paid holidays<br>10.  Paid sick leave: 72 hours of paid sick leave upon date of hire. Refreshes each calendar year. Unused balance will carry over each year up to a maximum cap of 112 hours.<br>11.  Paid parental leave<br>12.  Adoption assistance<br>13.  Employee Stock Purchase Plan<br>14.  Financial planning and group legal<br>15.  Voluntary benefits including auto, homeowner and pet insurance<br><br>The role will generally accept applications for at least three calendar days from the posting date or as long as the job remains posted.<p>Career Level - IC4</p><br>",
    "InternalQualificationsStr": "Disclaimer:<br><br><b>Certain US customer or client-facing roles may be required to comply with applicable requirements, such as immunization and occupational health mandates.</b><br><br><b>Range and benefit information provided in this posting are specific to the stated locations only</b><br><br>US: Hiring Range in USD from: $86,400 to $199,500 per annum. May be eligible for bonus and equity.<br><br>Oracle maintains broad salary ranges for its roles in order to account for variations in knowledge, skills, experience, market conditions and locations, as well as reflect Oracle's differing products, industries and lines of business.<br>Candidates are typically placed into the range based on the preceding factors as well as internal peer equity.<br><br>Oracle US offers a comprehensive benefits package which includes the following:<br>1.   Medical, dental, and vision insurance, including expert medical opinion<br>2.   Short term disability and long term disability<br>3.   Life insurance and AD&D<br>4.   Supplemental life insurance (Employee/Spouse/Child)<br>5.   Health care and dependent care Flexible Spending Accounts<br>6.   Pre-tax commuter and parking benefits<br>7.   401(k) Savings and Investment Plan with company match<br>8.   Paid time off: Flexible Vacation is provided to all eligible employees assigned to a salaried (non-overtime eligible) position. Accrued Vacation is provided to all other employees eligible for vacation benefits. For employees working at least 35 hours per week, the vacation accrual rate is 13 days annually for the first three years of employment and 18 days annually for subsequent years of employment. Vacation accrual is prorated for employees working between 20 and 34 hours per week. Employees working fewer than 20 hours per week are not eligible for vacation.<br>9.   11 paid holidays<br>10.  Paid sick leave: 72 hours of paid sick leave upon date of hire. Refreshes each calendar year. Unused balance will carry over each year up to a maximum cap of 112 hours.<br>11.  Paid parental leave<br>12.  Adoption assistance<br>13.  Employee Stock Purchase Plan<br>14.  Financial planning and group legal<br>15.  Voluntary benefits including auto, homeowner and pet insurance<br><br>The role will generally accept applications for at least three calendar days from the posting date or as long as the job remains posted.<p>Career Level - IC4</p><br>",
    "OrganizationDescriptionStr": "",
    "primaryLocationCoordinates": [
      {
        "Latitude": "39.82844",
        "Longitude": "-98.57939",
        "CountryCode": "US",
        "GeographyId": 300000000149325,
        "GeographyNodeId": 100257187667965
      }
    ],
    "ExternalResponsibilitiesStr": "<p><span style=\"font-size: 11pt;\"><strong>Responsibilities</strong></span></p><p><span style=\"font-size: 11pt;\">Work with the Site Reliability Engineering (SRE) team to take shared ownership of services and platform components. Develop a strong understanding of end-to-end system architecture, dependencies, and production behavior.</span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Design, build, and operate reliable, scalable, and secure infrastructure supporting large-scale analytics workloads</span></li><li><span style=\"font-size: 11pt;\">Improve system reliability through automation, monitoring, and performance optimization</span></li><li><span style=\"font-size: 11pt;\">Contribute to the adoption of AI-assisted approaches for operations, including:</span><ul style=\"list-style-type: circle;\"><li><span style=\"font-size: 11pt;\">Enhancing observability and alerting</span></li><li><span style=\"font-size: 11pt;\">Supporting automated incident detection and remediation</span></li><li><span style=\"font-size: 11pt;\">Exploring intelligent automation for infrastructure lifecycle management</span></li></ul></li><li><span style=\"font-size: 11pt;\">Partner with development teams to enhance service architecture, scalability, and operability</span></li><li><span style=\"font-size: 11pt;\">Participate in on-call rotations and act as an escalation point for complex production issues</span></li><li><span style=\"font-size: 11pt;\">Perform root cause analysis and implement long-term fixes to prevent recurrence</span></li><li><span style=\"font-size: 11pt;\">Apply knowledge of distributed systems to troubleshoot issues and optimize system performance</span></li><li><p><span style=\"font-size: 11pt;\">Drive continuous improvement in DevOps/SRE practices, including CI/CD, Infrastructure as Code, and automation at scale</span></p><p>&nbsp;</p></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Develop &amp; Maintain</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Implement and optimize infrastructure for Oracle HDI Analytics Platform&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Ensure system uptime, reliability, and scalability&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>AI-Driven Automation (NEW)</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Design and implement GenAI-powered or agent-based solutions for:&nbsp;</span><ul style=\"list-style-type: circle;\"><li><span style=\"font-size: 11pt;\">Observability and anomaly detection&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Incident triage and remediation&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Infrastructure provisioning and lifecycle management&nbsp;</span></li></ul></li><li><span style=\"font-size: 11pt;\">Build tools and frameworks that enable self-service and autonomous operations</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Data Pipeline Execution</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Build and optimize scalable data pipelines using Vertica and ETL frameworks&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Operational Excellence</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Apply DevOps/SRE practices to automate deployments and operations&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Enhance observability using Prometheus/Grafana and AI-driven insights&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Cloud Integration</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Support multi-cloud initiatives across OCI, AWS, and Azure&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Optimize cost, performance, and compliance across environments&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Incident Response</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Participate in on-call rotations&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Implement preventative and automated remediation solutions</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Collaboration</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Work closely with engineers to execute technical roadmaps&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Contribute to code reviews and infrastructure improvements&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>What You Bring</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">10+ years of software engineering experience, with 8+ years in cloud infrastructure, SRE, or DevOps&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Proven ownership of production system reliability in cloud environments&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Core Expertise</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Cloud infrastructure design and automation&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Distributed systems and performance optimization&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Data warehousing and ETL frameworks&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>AI-Native Experience</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Demonstrated experience applying GenAI / LLMs / agentic frameworks to infrastructure or operations&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Experience building or integrating AI-powered automation for DevOps/SRE workflows</span></li><li><span style=\"font-size: 11pt;\">Familiarity with tools like LangChain, AutoGPT, or custom AI agents&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Technical Skills</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Terraform, Docker, Kubernetes&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Observability stacks (Prometheus, Grafana)&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Python, Java, or Go&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Additional Strengths</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Strong problem-solving mindset with a focus on automation and scalability&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Experience improving system reliability through intelligent automation</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Preferred Qualifications</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Experience in healthcare or regulated environments (HIPAA, compliance frameworks)&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Familiarity with Oracle HDI or large-scale analytics platforms&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Experience working in environments requiring security clearance&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Experience building self-healing or autonomous infrastructure systems</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Why Join Oracle HDI?</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Own and shape AI-native SRE and automation strategy for a mission-critical platform&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Work on large-scale, data-intensive healthcare systems&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Be part of Oracle’s investment in AI-driven infrastructure and healthcare innovation</span></li><li><span style=\"font-size: 11pt;\">Build the future of autonomous, self-healing cloud platforms</span></li><li><span style=\"font-size: 11pt;\">Collaborate with top-tier engineers solving complex, real-world problems</span></li></ul><p>&nbsp;</p><p>Career Level - IC4</p>",
    "InternalResponsibilitiesStr": "<p><span style=\"font-size: 11pt;\"><strong>Responsibilities</strong></span></p><p><span style=\"font-size: 11pt;\">Work with the Site Reliability Engineering (SRE) team to take shared ownership of services and platform components. Develop a strong understanding of end-to-end system architecture, dependencies, and production behavior.</span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Design, build, and operate reliable, scalable, and secure infrastructure supporting large-scale analytics workloads</span></li><li><span style=\"font-size: 11pt;\">Improve system reliability through automation, monitoring, and performance optimization</span></li><li><span style=\"font-size: 11pt;\">Contribute to the adoption of AI-assisted approaches for operations, including:</span><ul style=\"list-style-type: circle;\"><li><span style=\"font-size: 11pt;\">Enhancing observability and alerting</span></li><li><span style=\"font-size: 11pt;\">Supporting automated incident detection and remediation</span></li><li><span style=\"font-size: 11pt;\">Exploring intelligent automation for infrastructure lifecycle management</span></li></ul></li><li><span style=\"font-size: 11pt;\">Partner with development teams to enhance service architecture, scalability, and operability</span></li><li><span style=\"font-size: 11pt;\">Participate in on-call rotations and act as an escalation point for complex production issues</span></li><li><span style=\"font-size: 11pt;\">Perform root cause analysis and implement long-term fixes to prevent recurrence</span></li><li><span style=\"font-size: 11pt;\">Apply knowledge of distributed systems to troubleshoot issues and optimize system performance</span></li><li><p><span style=\"font-size: 11pt;\">Drive continuous improvement in DevOps/SRE practices, including CI/CD, Infrastructure as Code, and automation at scale</span></p><p>&nbsp;</p></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Develop &amp; Maintain</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Implement and optimize infrastructure for Oracle HDI Analytics Platform&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Ensure system uptime, reliability, and scalability&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>AI-Driven Automation (NEW)</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Design and implement GenAI-powered or agent-based solutions for:&nbsp;</span><ul style=\"list-style-type: circle;\"><li><span style=\"font-size: 11pt;\">Observability and anomaly detection&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Incident triage and remediation&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Infrastructure provisioning and lifecycle management&nbsp;</span></li></ul></li><li><span style=\"font-size: 11pt;\">Build tools and frameworks that enable self-service and autonomous operations</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Data Pipeline Execution</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Build and optimize scalable data pipelines using Vertica and ETL frameworks&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Operational Excellence</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Apply DevOps/SRE practices to automate deployments and operations&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Enhance observability using Prometheus/Grafana and AI-driven insights&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Cloud Integration</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Support multi-cloud initiatives across OCI, AWS, and Azure&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Optimize cost, performance, and compliance across environments&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Incident Response</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Participate in on-call rotations&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Implement preventative and automated remediation solutions</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Collaboration</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Work closely with engineers to execute technical roadmaps&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Contribute to code reviews and infrastructure improvements&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>What You Bring</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">10+ years of software engineering experience, with 8+ years in cloud infrastructure, SRE, or DevOps&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Proven ownership of production system reliability in cloud environments&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Core Expertise</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Cloud infrastructure design and automation&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Distributed systems and performance optimization&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Data warehousing and ETL frameworks&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>AI-Native Experience</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Demonstrated experience applying GenAI / LLMs / agentic frameworks to infrastructure or operations&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Experience building or integrating AI-powered automation for DevOps/SRE workflows</span></li><li><span style=\"font-size: 11pt;\">Familiarity with tools like LangChain, AutoGPT, or custom AI agents&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Technical Skills</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Terraform, Docker, Kubernetes&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Observability stacks (Prometheus, Grafana)&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Python, Java, or Go&nbsp;</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Additional Strengths</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Strong problem-solving mindset with a focus on automation and scalability&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Experience improving system reliability through intelligent automation</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Preferred Qualifications</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Experience in healthcare or regulated environments (HIPAA, compliance frameworks)&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Familiarity with Oracle HDI or large-scale analytics platforms&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Experience working in environments requiring security clearance&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Experience building self-healing or autonomous infrastructure systems</span></li></ul><p>&nbsp;</p><p><span style=\"font-size: 11pt;\"><strong>Why Join Oracle HDI?</strong></span></p><ul style=\"list-style-type: disc;\"><li><span style=\"font-size: 11pt;\">Own and shape AI-native SRE and automation strategy for a mission-critical platform&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Work on large-scale, data-intensive healthcare systems&nbsp;</span></li><li><span style=\"font-size: 11pt;\">Be part of Oracle’s investment in AI-driven infrastructure and healthcare innovation</span></li><li><span style=\"font-size: 11pt;\">Build the future of autonomous, self-healing cloud platforms</span></li><li><span style=\"font-size: 11pt;\">Collaborate with top-tier engineers solving complex, real-world problems</span></li></ul><p>&nbsp;</p><p>Career Level - IC4</p>",
    "InternationalTravelRequired": null
  },
  "list_job": {
    "Id": "328742",
    "Title": "Principal Infrastructure & Reliability Engineer",
    "JobType": null,
    "Distance": 1780617600000,
    "JobShift": null,
    "Language": "US",
    "WorkDays": null,
    "JobFamily": null,
    "Relevancy": 9,
    "WorkHours": null,
    "Department": null,
    "HotJobFlag": false,
    "PostedDate": "2026-06-05",
    "StudyLevel": null,
    "WorkerType": null,
    "GeographyId": 300000000149325,
    "JobFunction": null,
    "JobSchedule": null,
    "BusinessUnit": null,
    "ContractType": null,
    "ManagerLevel": null,
    "Organization": null,
    "TrendingFlag": false,
    "workLocation": [],
    "LegalEmployer": null,
    "MediaThumbURL": "https://img.youtube.com/vi/BV0GMCITXg4/hqdefault.jpg",
    "WorkplaceType": "",
    "BusinessUnitId": 300001096431127,
    "OrganizationId": 300001902541887,
    "PostingEndDate": null,
    "LegalEmployerId": 300000000482027,
    "PrimaryLocation": "United States",
    "WorkDurationYears": null,
    "WorkplaceTypeCode": null,
    "BeFirstToApplyFlag": false,
    "WorkDurationMonths": null,
    "otherWorkLocations": [],
    "secondaryLocations": [],
    "ShortDescriptionStr": "Join Oracle's Health Data Intelligence (HDI) team as a Software Engineer 4, focused on Site Reliability Engineering for large-scale healthcare analytics platforms. In this role, you will design, build, and operate highly reliable, scalable infrastructure and data pipelines that power mission-critical analytics globally.\nYou will also contribute to the next evolution of cloud operations by advancing automation, observability, and AI-assisted reliability practices. This includes exploring the use of Generative AI and intelligent automation to improve incident response, system resilience, and operational efficiency.\nYou will work within a collaborative team to deliver robust solutions that handle massive datasets with precision and performance, while continuously improving system reliability and operational excellence.",
    "requisitionFlexFields": [],
    "DomesticTravelRequired": null,
    "PrimaryLocationCountry": "US",
    "ExternalQualificationsStr": null,
    "ExternalResponsibilitiesStr": null,
    "InternationalTravelRequired": null
  },
  "detail_meta": {
    "url": "https://eeho.fa.us2.oraclecloud.com/hcmRestApi/resources/latest/recruitingCEJobRequisitionDetails?expand=all&onlyData=true&finder=ById;Id=%22328742%22,siteNumber=CX_1",
    "http_status": 200,
    "content_type": "application/json",
    "response_bytes": 32020
  },
  "detail_errors": []
}