{"id":2287307,"url":"https://alion.io/job/itmatch-senior-site-reliability-engineer","title":"Senior Site Reliability Engineer","company":{"id":4409143,"name":"itMatch","domain":"itmatch.com","url":"https://alion.io/company/itmatch","size_band":"11-50","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"DevOps","role_family":"DevOps","seniority":"senior","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"posting_text","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":["Kraków, Poland"],"countries":["PL"],"hiring_countries":["PL"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":66000,"max_usd":103000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":80},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"CI/CD","optional":false},{"name":"Grafana","optional":false},{"name":"Incident Management","optional":false},{"name":"Kubernetes","optional":false},{"name":"Platform Engineering","optional":false},{"name":"Prometheus","optional":false},{"name":"Python","optional":false},{"name":"SLI/SLO/SLA","optional":false},{"name":"Terraform","optional":false}],"status":"live","first_seen_at":"2026-10-11T11:45:12Z","employer_posted_date":null,"last_verified_at":"2026-10-11T11:45:12Z","board_verified":false,"closed_at":null,"days_open":0,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":0},"description":"Remote work only from within Poland\nDo you enjoy solving complex reliability challenges for cutting-edge technology?\nDo you have a passion for automation and building systems that scale?\nAs a Senior SRE, responsibilities include owning reliability workstreams for the company's serverless inference platform, building automation and tooling, and contributing to architecture and operational decisions. Opportunities exist to take ownership of critical reliability problems end-to-end, partner with product engineering teams, and develop expertise in GPU infrastructure, Kubernetes at scale, and AI inference workloads.\nAs a Site Reliability Engineer, you will be responsible for:\nBuilding and maintaining observability for AI workloads, including telemetry, dashboards, alerts, SLO/SLI tracking, and driving improvements when targets are missed\n\nWriting automation and tooling to reduce operational toil, improve deployment safety, and accelerate incident response\n\nIntegrating AI workloads into our existing incident management processes, building runbooks, participating in on-call rotations, and conducting blameless post-mortems\n\nBuilding and maintaining CI/CD integrations, deployment safety checks, and rollback automation\n\nCollaborating with product engineering teams to improve reliability, contribute to architecture decisions, and ensure operational readiness for product releases\n\nContributing to capacity planning, autoscaling configuration, and workload scheduling for AI compute infrastructure\n\nDo what you love\nTo be successful in this role you will:\nDemonstrate expertise in SRE, infrastructure, or platform engineering, managing large-scale distributed systems with extensive operational experience.\n\nDemonstrate expertise in Kubernetes and large-scale containerization systems.\n\nDefine SLOs and work with observability tools like Prometheus, Grafana, and distributed tracing to enhance system monitoring.\n\nDemonstrate proficiency in Python or Go for automation, CI/CD pipelines, deployment safety, and infrastructure-as-code like Terraform.\n\nInterest in or experience with AI/ML infrastructure, model serving, or GPU workloads\n\nResolve issues independently while maintaining accountability throughout the process.\n\nDemonstrate accountability for reliability, develop automation and monitoring, and collaborate effectively with an engineering team unfamiliar with SRE practices.\n\nWorking for you\nWe will provide you with opportunities to grow, flourish, and achieve great things. Our benefit options are designed to meet your individual needs for today and in the future. We provide benefits surrounding all aspects of your life:\nYour health\n\nYour finances\n\nYour family\n\nYour time at work\n\nYour time pursuing other endeavors\n\nOur benefit plan options are designed to meet your individual needs and budget, both today and in the future.\n\nTech stack\nAI\nGPU\nKubernetes\nPython\nLinux","description_format":"text","description_chars":2895,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"Poland","iso":"PL","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-10-11T14:25:01Z"}],"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":7,"reasons":["seen:0","win:early"],"computed_at":"2026-10-12T06:10:43Z"},"pay":null,"html_url":"https://alion.io/job/itmatch-senior-site-reliability-engineer","json_url":"https://alion.io/job/itmatch-senior-site-reliability-engineer.json","meta":{"generated_at":"2026-10-12T06:10:43Z","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":9887,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-13T00:00:00Z"}},"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":4409143},"rest":"https://alion.io/mcp/rest/get_company?id=4409143"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fitmatch-senior-site-reliability-engineer"},{"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%2Fitmatch-senior-site-reliability-engineer"},{"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%2Fitmatch-senior-site-reliability-engineer"},{"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/itmatch-senior-site-reliability-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fitmatch-senior-site-reliability-engineer"}]}