{"id":4480553,"url":"https://alion.io/job/htc-global-services-site-reliability-engineering-manager","title":"Site Reliability Engineering Manager","company":{"id":4199,"name":"HTC Global Services","domain":"htcinc.com","url":"https://alion.io/company/htc-global-services","size_band":"5000+","is_staffing_agency":false,"employer_type":"services","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"Leadership","role_family":"Leadership","seniority":"lead","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Hyderabad, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Amazon CloudWatch","optional":false},{"name":"Datadog","optional":false},{"name":"Dynatrace","optional":false},{"name":"Incident Management","optional":false},{"name":"ITSM","optional":false},{"name":"New Relic","optional":false},{"name":"PagerDuty","optional":false},{"name":"Prometheus","optional":false},{"name":"Rest API","optional":false},{"name":"ServiceNow","optional":false},{"name":"Splunk","optional":false}],"status":"live","first_seen_at":"2026-11-17T18:35:30Z","employer_posted_date":null,"last_verified_at":"2026-11-17T18:35:30Z","board_verified":false,"closed_at":null,"days_open":0,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":0},"description":"We are looking for a highly skilled Lead PagerDuty Implementation Engineer to drive a large-scale enterprise implementation and migration initiative. This individual will serve as the primary technical anchor for the PagerDuty platform, leading architecture, configuration, integration, migration, and production rollout activities.\n\nThe ideal candidate will have deep hands-on experience implementing PagerDuty in enterprise environments, designing event orchestration workflows, integrating monitoring and ITSM platforms, and driving successful production deployments.\n\nKey Responsibilities:\nServe as the technical lead for enterprise PagerDuty implementation initiatives.\nAssess existing Moogsoft capabilities and design equivalent or enhanced solutions within PagerDuty.\nOwn PagerDuty platform architecture, configuration standards, and implementation best practices.\nDesign and configure Event Orchestration, Event Routing, Correlation, Deduplication, and Suppression rules.\nConfigure services, teams, business services, schedules, escalation policies, and responder workflows.\nLead technical decision-making throughout implementation and migration programs.\nPartner with Monitoring, SRE, Operations, Automation, and ServiceNow teams to ensure seamless integration.\nDrive migration planning, production cutover strategy, hypercare, and stabilization activities.\nDevelop technical documentation, operational runbooks, and knowledge transfer materials.\nEnsure all technical deliverables meet agreed project milestones and business outcomes.\n\nRequired Skills:\n\nMandatory:\n5+ years of hands-on PagerDuty implementation experience.\nStrong expertise in PagerDuty Event Orchestration.\nExperience with Event Routing, Correlation, Deduplication, and Suppression.\nHands-on experience configuring:\nServices\nBusiness Services\nTeams\nEscalation Policies\nOn-call Schedules\nIncident Response Workflows\nExperience integrating PagerDuty using REST APIs.\nExperience with enterprise-scale production implementations.\nStrong stakeholder communication and technical leadership skills.\n\nPreferred:\nMoogsoft to PagerDuty migration experience.\nServiceNow integration experience.\nExperience with Datadog, Splunk, Dynatrace, New Relic, Prometheus, or CloudWatch.\nBackground in SRE, Observability, Incident Management, or Production Operations.\n\nWhat Success Looks Like:\nSuccessful migration from existing event management platforms.\nReduced alert noise through effective event correlation and suppression.\nImproved incident response effectiveness.\nWell-documented and scalable PagerDuty operating model.\nSmooth production rollout with minimal business disruption.\nSkills\nEvent Orchestration, PagerDuty, REST API, REST APIs","description_format":"text","description_chars":2700,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["IT Consulting & Digital Transformation","IT Outsourcing & Dedicated Teams","Business Process Outsourcing (BPO)"],"lifecycle":[{"event":"open","at":"2026-11-17T18:35:30Z"}],"visa":[],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":20,"reasons":["seen:0","win:early"],"computed_at":"2026-11-17T20:13:16Z"},"pay":null,"html_url":"https://alion.io/job/htc-global-services-site-reliability-engineering-manager","json_url":"https://alion.io/job/htc-global-services-site-reliability-engineering-manager.json","meta":{"generated_at":"2026-11-17T20:13:16Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":2212,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-18T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.1,"usd":0.01,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":4199},"rest":"https://alion.io/mcp/rest/get_company?id=4199"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fhtc-global-services-site-reliability-engineering-manager"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"free","price":{"credits":0,"usd":0},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fhtc-global-services-site-reliability-engineering-manager"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.1,"usd":0.01},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fhtc-global-services-site-reliability-engineering-manager"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/htc-global-services-site-reliability-engineering-manager\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fhtc-global-services-site-reliability-engineering-manager"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":4480553}},{"tool":"search_jobs","arguments":{"company":"htcinc.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":4480553},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}