[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"job-resiliency-engineer-keybank-national-association-en-us":3},{"id":4,"slug":5,"title":6,"description":7,"company":8,"is_featured":11,"featured_until":7,"is_active":12,"deactivated_at":7,"is_enriched":12,"processed_job_posting_json":13,"processed_latitude":84,"processed_longitude":85,"processed_employment_types":86,"processed_working_hours":87,"processed_working_hours_labels":89,"processed_home_office":90,"processed_salary_min":81,"processed_salary_max":82,"processed_salary_currency":78,"processed_salary_source":91,"processed_benefits":92,"processed_benefits_labels":96,"processed_industry":97,"processed_skills":7,"processed_job_location":98,"processed_full_address_gmaps":100,"processed_street_gmaps":102,"processed_city_gmaps":104,"processed_postal_code_gmaps":105,"processed_country_gmaps":107,"processed_country_iso_code_gmaps":109,"full_description":16,"formatted_description":110,"processed_employment_types_labels":36,"processed_home_office_labels":34,"processed_industry_labels":38,"processed_it_skills":111,"processed_it_skills_labels":114,"processed_soft_skills":115,"processed_soft_skills_labels":116,"processed_job_expertise_skills":117,"processed_job_expertise_skills_labels":118,"processed_language_requirements":119,"processed_total_experience_years":112,"processed_professional_field":126,"processed_professional_field_labels":129,"processed_leadership_role":11,"processed_date_posted":20,"raw_job_url":130,"apply_url":7,"raw_hiringOrganization_logo_url":7,"translations":7,"canonical_industry_key":131,"canonical_industry_label":132,"max_cpc":133,"actual_cpc":7},85090,"resiliency-engineer-keybank-national-association","Resiliency Engineer",null,{"name":9,"slug":10,"logo_url":7},"KeyBank National Association","keybank-national-association",false,true,{"@context":14,"@type":15,"title":6,"description":16,"hiringOrganization":17,"datePosted":20,"validThrough":21,"jobLocation":22,"jobLocationType":34,"employmentType":35,"industry":37,"skills":39,"baseSalary":76},"https:\u002F\u002Fschema.org\u002F","JobPosting","Location: 555 Patroon Creek Boulevard, Albany New York Position Summary The Resiliency Engineer designs, builds, and continuously improves the reliability, availability, and recoverability of KeyBank’s technology platforms across on-premises, hybrid, and cloud (GCP\u002FAzure) environments. Applying software engineering discipline to operations, this role engineers systems to meet defined recovery objectives, automates recovery and validation, and proves that critical services can withstand and recover from failure. This is a hands-on engineering role for a builder who can write automation, reason about distributed-system failure modes, and facilitate across application, infrastructure, architecture, cloud, and line-of-business teams. The ideal candidate is equally comfortable in code, in a design review, and in a command center during a live recovery exercise. Key Responsibilities Automation & Engineering Design and code automation that reduces operational toil and replaces manual, error-prone runbooks with orchestrated, auditable failover and recovery workflows. Develop and maintain infrastructure-as-code, scripts, and pipelines (e.g., Python, Bash, PowerShell, Terraform, Ansible) to provision, configure, and validate recovery environments. Build self-healing patterns, health checks, and automated validation that confirm recoverability before a disaster is ever declared. Reliability & Resiliency Design Partner with application and infrastructure teams to assess system architecture for reliability, redundancy, and recoverability against assigned system criticality. Define, measure, and support Service Level Indicators (SLIs), Service Level Objectives (SLOs), and error budgets for critical services. Ensure architecture is selected to meet Recovery Time Objective (RTO) and Recovery Point Objective (RPO) targets. Testing, Chaos & Validation Plan and execute disaster recovery tests and targeted fault-injection \u002F chaos experiments (e.g., zonal failure, load-balancer, regional failover) to proactively expose weaknesses. Improve monitoring, alerting, and observability to detect service degradation early. Facilitation & Partnership Facilitate resiliency and architecture reviews, tabletop exercises, and cross-team recovery walkthroughs, aligning technical and business stakeholders toward clear outcomes. Provide subject-matter expertise on reliability engineering practices and drive adoption across technology teams. Produce clear, examiner-ready documentation and evidence, ensuring work aligns with KeyBank policies, standards, and regulatory requirements. Required Qualifications Bachelor’s degree in Computer Science, Information Technology, Engineering, or related field—or equivalent work experience. Demonstrated experience in reliability engineering, DevOps, infrastructure, or technology operations. Hands-on coding and automation ability (e.g., Python, Bash, PowerShell) and experience with infrastructure-as-code (e.g., Terraform, Ansible). Working knowledge of BOTH on-premises infrastructure (compute, storage, network, virtualization, databases) AND public cloud platforms (GCP and\u002For Azure). Understanding of high-availability design: redundancy, replication, failover, and load balancing. Strong facilitation, analytical, problem-solving, and written\u002Fverbal communication skills, with the ability to influence across teams. Preferred Qualifications Experience with site reliability engineering principles and service-level management (SLIs, SLOs, error budgets). Experience with disaster recovery planning, resiliency testing, or chaos \u002F fault-injection engineering (e.g., Google FIT, Gremlin). Familiarity with containers and orchestration (Kubernetes\u002FGKE), CI\u002FCD, and observability tooling (e.g., Dynatrace, Prometheus, Grafana, Splunk). Experience with ServiceNow (ITOM \u002F Business Continuity Management) or comparable orchestration platforms. Experience in a regulated industry or large, complex enterprise environment; familiarity with FFIEC, NIST SP 800-34\u002FCSF, or ISO 22301. Relevant certifications (e.g., cloud architect\u002Fengineer, Kubernetes, Linux, ITIL). COMPENSATION AND BENEFITS This position is eligible to earn a base salary in the range of $63,000.00 - $96,000.00 annually. Placement within the pay range may differ based upon various factors, including but not limited to skills, experience and geographic location. Compensation for this role also includes eligibility for incentive compensation which may include production, commission, and\u002For discretionary incentives. Please click here for a list of benefits for which this position is eligible. Key has implemented an approach to employee workspaces which prioritizes in-office presence, while providing flexible options in circumstances where roles can be performed effectively in a mobile environment. Job Posting Expiration Date: 10\u002F30\u002F2026 KeyCorp is an Equal Opportunity Employer committed to sustaining an inclusive culture. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, genetic information, pregnancy, disability, veteran status or any other characteristic protected by law. Qualified individuals with disabilities or disabled veterans who are unable or limited in their ability to apply on this site may request reasonable accommodations by emailing HR_Compliance@keybank.com. #LI-Remote KeyBank is an organization collectively committed to helping you unlock your potential and discover what truly drives you. Working here means sharing our purpose to help our clients, colleagues, and communities thrive. You’ll find genuinely supportive teammates, a flexible, inclusive work environment, challenging projects, accessible leaders, and opportunities to grow in your position and your career. For 200 years, Key has opened doors in our communities. Let us open one for you.",{"@type":18,"name":19},"Organization","0100 KeyBank National Association","2026-09-24","2027-09-24",[23],{"@type":24,"address":25,"geo":30},"Place",{"@type":26,"addressLocality":27,"addressCountry":28,"addressRegion":29},"PostalAddress","Albany","US","New York",{"@type":31,"latitude":32,"longitude":33},"GeoCoordinates",42.6829162,-73.80664589999999,"HYBRID",[36],"PERMANENT",[38],"Banking and Financial Services",[40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75],"Python","Bash","PowerShell","Terraform","Ansible","GCP","Azure","Kubernetes","GKE","CI\u002FCD","Dynatrace","Prometheus","Grafana","Splunk","ServiceNow","Facilitation","Analytical","Problem-solving","Written Communication","Verbal Communication","Influence","Collaboration","Reliability Engineering","DevOps","Infrastructure Management","Technology Operations","Infrastructure-as-Code","High-Availability Design","Disaster Recovery Planning","Resiliency Testing","Chaos Engineering","Site Reliability Engineering","Service Level Management","Observability","Regulatory Compliance","ITIL",{"@type":77,"currency":78,"value":79},"MonetaryAmount","USD",{"@type":80,"minValue":81,"maxValue":82,"unitText":83},"QuantitativeValue",63000,96000,"YEAR",[32],[33],"permanent",[88],"FULL_TIME",[88],"hybrid","estimated",[93,94,95],"Incentive compensation (production, commission, and\u002For discretionary incentives)","Flexible work options","Comprehensive benefits package (details via link)",[93,94,95],"banking and financial services",[99],"0100, 555 patroon creek boulevard, albany, ny, united states of america",[101],"555 Patroon Creek Blvd, Albany, NY 12206, USA",[103],"Patroon Creek Boulevard 555",[27],[106],"12206",[108],"USA",[28],"Location: 555 Patroon Creek Boulevard, Albany New York\n\n## Position Summary\n\nThe Resiliency Engineer designs, builds, and continuously improves the reliability, availability, and recoverability of KeyBank’s technology platforms across on-premises, hybrid, and cloud (GCP\u002FAzure) environments. Applying software engineering discipline to operations, this role engineers systems to meet defined recovery objectives, automates recovery and validation, and proves that critical services can withstand and recover from failure. This is a hands-on engineering role for a builder who can write automation, reason about distributed-system failure modes, and facilitate across application, infrastructure, architecture, cloud, and line-of-business teams. The ideal candidate is equally comfortable in code, in a design review, and in a command center during a live recovery exercise.\n\n## Key Responsibilities\n\n### Automation & Engineering\n\n- Design and code automation that reduces operational toil and replaces manual, error-prone runbooks with orchestrated, auditable failover and recovery workflows.\n- Develop and maintain infrastructure-as-code, scripts, and pipelines (e.g., Python, Bash, PowerShell, Terraform, Ansible) to provision, configure, and validate recovery environments.\n- Build self-healing patterns, health checks, and automated validation that confirm recoverability before a disaster is ever declared.\n\n### Reliability & Resiliency Design\n\n- Partner with application and infrastructure teams to assess system architecture for reliability, redundancy, and recoverability against assigned system criticality.\n- Define, measure, and support Service Level Indicators (SLIs), Service Level Objectives (SLOs), and error budgets for critical services.\n- Ensure architecture is selected to meet Recovery Time Objective (RTO) and Recovery Point Objective (RPO) targets.\n\n### Testing, Chaos & Validation\n\n- Plan and execute disaster recovery tests and targeted fault-injection \u002F chaos experiments (e.g., zonal failure, load-balancer, regional failover) to proactively expose weaknesses.\n- Improve monitoring, alerting, and observability to detect service degradation early.\n\n### Facilitation & Partnership\n\n- Facilitate resiliency and architecture reviews, tabletop exercises, and cross-team recovery walkthroughs, aligning technical and business stakeholders toward clear outcomes.\n- Provide subject-matter expertise on reliability engineering practices and drive adoption across technology teams.\n- Produce clear, examiner-ready documentation and evidence, ensuring work aligns with KeyBank policies, standards, and regulatory requirements.\n\n## Required Qualifications\n\n- Bachelor’s degree in Computer Science, Information Technology, Engineering, or related field—or equivalent work experience.\n- Demonstrated experience in reliability engineering, DevOps, infrastructure, or technology operations.\n- Hands-on coding and automation ability (e.g., Python, Bash, PowerShell) and experience with infrastructure-as-code (e.g., Terraform, Ansible).\n- Working knowledge of BOTH on-premises infrastructure (compute, storage, network, virtualization, databases) AND public cloud platforms (GCP and\u002For Azure).\n- Understanding of high-availability design: redundancy, replication, failover, and load balancing.\n- Strong facilitation, analytical, problem-solving, and written\u002Fverbal communication skills, with the ability to influence across teams.\n\n## Preferred Qualifications\n\n- Experience with site reliability engineering principles and service-level management (SLIs, SLOs, error budgets).\n- Experience with disaster recovery planning, resiliency testing, or chaos \u002F fault-injection engineering (e.g., Google FIT, Gremlin).\n- Familiarity with containers and orchestration (Kubernetes\u002FGKE), CI\u002FCD, and observability tooling (e.g., Dynatrace, Prometheus, Grafana, Splunk).\n- Experience with ServiceNow (ITOM \u002F Business Continuity Management) or comparable orchestration platforms.\n- Experience in a regulated industry or large, complex enterprise environment; familiarity with FFIEC, NIST SP 800-34\u002FCSF, or ISO 22301.\n- Relevant certifications (e.g., cloud architect\u002Fengineer, Kubernetes, Linux, ITIL).\n\n## COMPENSATION AND BENEFITS\n\nThis position is eligible to earn a base salary in the range of $63,000.00 - $96,000.00 annually. Placement within the pay range may differ based upon various factors, including but not limited to skills, experience and geographic location. Compensation for this role also includes eligibility for incentive compensation which may include production, commission, and\u002For discretionary incentives. Please click here for a list of benefits for which this position is eligible.\n\nKey has implemented an approach to employee workspaces which prioritizes in-office presence, while providing flexible options in circumstances where roles can be performed effectively in a mobile environment.\n\nJob Posting Expiration Date: 10\u002F30\u002F2026\n\nKeyCorp is an Equal Opportunity Employer committed to sustaining an inclusive culture. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, genetic information, pregnancy, disability, veteran status or any other characteristic protected by law. Qualified individuals with disabilities or disabled veterans who are unable or limited in their ability to apply on this site may request reasonable accommodations by emailing HR_Compliance@keybank.com.\n\n#LI-Remote\n\nKeyBank is an organization collectively committed to helping you unlock your potential and discover what truly drives you. Working here means sharing our purpose to help our clients, colleagues, and communities thrive. You’ll find genuinely supportive teammates, a flexible, inclusive work environment, challenging projects, accessible leaders, and opportunities to grow in your position and your career. For 200 years, Key has opened doors in our communities. Let us open one for you.",{"gcp":112,"gke":112,"bash":113,"azure":112,"ci\u002Fcd":112,"python":113,"splunk":112,"ansible":113,"grafana":112,"dynatrace":112,"terraform":113,"kubernetes":112,"powershell":113,"prometheus":112,"servicenow":112},3,4,[40,41,42,43,44,45,46,47,48,49,50,51,52,53,54],{"facilitation":113,"analytical":113,"problem-solving":113,"written communication":113,"verbal communication":113,"influence":113,"collaboration":113},[55,56,57,58,59,60,61],{"itil":112,"devops":113,"observability":112,"chaos engineering":112,"resiliency testing":113,"regulatory compliance":112,"technology operations":113,"infrastructure-as-code":113,"reliability engineering":113,"high-availability design":113,"service level management":112,"infrastructure management":113,"disaster recovery planning":113,"site reliability engineering":112},[62,63,64,65,66,67,68,69,70,71,72,73,74,75],{"detected_language_jobad":120,"required":121},"en",[122],[123],{"language":124,"level":125},"ENGLISH","C2",[127,128],"Information and Communications Technology Professionals","Engineering Professionals",[127,128],"https:\u002F\u002Fkeybank.wd5.myworkdayjobs.com\u002Fen-us\u002Fexternal_career_site\u002Fjob\u002Falbany-ny\u002Fresiliency-engineer_r-41921","banking","Banking",1]