{"id":2201584,"url":"https://alion.io/job/madiff-site-reliability-engineer-ai","title":"Site Reliability Engineer (AI)","company":{"id":4374669,"name":"Madiff","domain":"madiff.eu","url":"https://alion.io/company/madiff-2","size_band":"51-200","is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Zoho Recruit","truth_index":null},"role":"DevOps","role_family":"DevOps","seniority":"senior","employment_type":"full_time","work_mode":"remote","remote_scope":"unspecified","remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":[],"countries":[],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":81000,"max_usd":193000,"period":"year","method":"global_role_seniority_cell","sample_n":2792},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Azure","optional":false},{"name":"Azure DevOps","optional":false},{"name":"CI/CD","optional":false},{"name":"Datadog","optional":false},{"name":"Incident Management","optional":false},{"name":"Kubernetes","optional":false},{"name":"Grafana","optional":true},{"name":"LLM","optional":true}],"status":"live","first_seen_at":"2026-10-09T21:24:31Z","employer_posted_date":"2026-10-13","last_verified_at":"2026-10-13T19:41:08Z","board_verified":true,"closed_at":null,"days_open":4,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":4},"description":"This is a remote position.\nWe are looking for a Senior Site Reliability Engineer to support advanced AI platforms responsible for production-grade applications and pipelines. The role focuses on building and maintaining reliability, scalability, and operational excellence across multiple AI-driven systems.\nThe engineer will work on a central operational layer for monitoring and managing AI workloads, improving system stability, and reducing incidents. This is a hands-on role requiring direct involvement in diagnosing production issues, implementing fixes, and optimising monitoring, alerting, and CI/CD processes.\nThe position requires close collaboration with engineering teams to improve release quality, standardise telemetry, and ensure stable and predictable system behaviour in a distributed cloud environment.\nResponsibilities\nBuild and maintain central monitoring and alerting layer for AI applications and pipelines\nDefine and implement SLIs, alerts, and operational dashboards\nManage incidents including triage, coordination, root cause analysis, and prevention\nStandardise telemetry across systems including latency, throughput, and failures\nOptimise CI CD pipelines and introduce quality gates for reliability\nWork closely with engineering teams to reduce recurring issues and improve stability\nRequirements\nMinimum5+ years of experience in SRE, Platform, or Production Engineering\nStrong hands on experience withKubernetes and production environments\nExperience withAzure and Azure DevOps\nExperience with monitoring tools such asDatadog\nStrong understanding ofincident management and root cause analysis\nAbility to build practical monitoring and alerting systems\nNice to have\nExperience withAI or LLM pipelines\nExperience building monitoring platforms across multiple systems\nExperience withGrafana\nExperience working in large scale or distributed environments\nExpectations\nStrong ownership mindset and accountability for system stability\nProactive approach to identifying risks and improvements\nHands on engineer actively working with systems, not only coordinating\nComfortable working in dynamic and evolving environments\nBenefits\nSolid, competitive salary\nWork in a multinational environment on international projects\nComprehensive healthcare\nLong-term B2B contract with a stable project pipeline\nWork model: fully remote","description_format":"text","description_chars":2343,"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":["Artificial Intelligence"],"lifecycle":[{"event":"open","at":"2026-10-09T21:24:31Z"}],"visa":[],"liveness":{"score":52,"band":"ok","label":"Likely open","p_open":1,"p_active":0.516,"p_room":1,"age_days":3,"expected_fill_days":35,"reasons":["conf:1","agency","win:early","comp:brand"],"computed_at":"2026-10-13T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/madiff-site-reliability-engineer-ai","json_url":"https://alion.io/job/madiff-site-reliability-engineer-ai.json","meta":{"generated_at":"2026-10-13T22:16:20Z","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":33977,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-14T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"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":4374669},"rest":"https://alion.io/mcp/rest/get_company?id=4374669"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fmadiff-site-reliability-engineer-ai"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"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%2Fmadiff-site-reliability-engineer-ai"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"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%2Fmadiff-site-reliability-engineer-ai"},{"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/madiff-site-reliability-engineer-ai\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fmadiff-site-reliability-engineer-ai"}]}