{"id":734436,"url":"https://alion.io/job/boson-site-reliability-engineer","title":"Site Reliability Engineer","company":{"id":669673,"name":"Boson AI","domain":"boson.ai","url":"https://alion.io/company/boson-2","size_band":"11-50","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Lever","truth_index":{"grade":"C","score":64,"open_postings":10,"ghost_share":0.6,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-30T05:48:23Z"}},"role":"DevOps","role_family":"DevOps","seniority":"middle","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Toronto, Canada"],"countries":["CA"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":125000,"max":250000,"currency":"CAD","period":"year","gross":null,"usd_annual":175444},"salary_estimate":null,"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"BGP","optional":false},{"name":"Configuration Management","optional":false},{"name":"CUDA","optional":false},{"name":"InfiniBand","optional":false},{"name":"Kubernetes","optional":false},{"name":"Linux","optional":false},{"name":"SLURM","optional":false},{"name":"SRE","optional":false},{"name":"Ansible","optional":true},{"name":"AWS","optional":true},{"name":"Azure","optional":true},{"name":"GCP","optional":true},{"name":"Grafana","optional":true},{"name":"HPC","optional":true},{"name":"NCCL","optional":true},{"name":"Prometheus","optional":true},{"name":"Terraform","optional":true}],"status":"live","first_seen_at":"2026-07-14T18:54:35Z","employer_posted_date":"2026-07-14","last_verified_at":"2026-10-31T01:35:47Z","board_verified":true,"closed_at":null,"days_open":108,"trust":{"level":"ghost","repost_count":0,"flags":["stale","company_stale"],"days_open":106},"description":"About The Role\nBoson AI builds production-grade AI systems that make communication with AI more natural, capable, and useful. We are looking for a Site Reliability Engineer to help build and operate the infrastructure behind that work.\nBased in Toronto or remote, you will work across the systems that enable large-scale AI training and serving: high-performance networks, GPU clusters, storage, scheduling, and the operational tooling that keeps them reliable. This is a hands-on role for someone who enjoys taking complex infrastructure from “it works” to dependable, observable, and scalable.\nYou do not need to be an expert in every layer of the stack. We are looking for deep strength in at least one area-networking, cluster scheduling, storage, GPU systems, or AI infrastructure- and the curiosity and judgment to collaborate across the rest.\nResponsibilities\nDesign, operate, and improve reliable infrastructure for AI training and inference workloads\nOwn and automate operational workflows across one or more core areas: networking, compute allocation, storage, GPU/server configuration, or AI platforms\nBuild monitoring, alerting, runbooks, and incident-response practices that make systems easier to operate\nDiagnose performance, capacity, and reliability issues across hardware, operating systems, networks, schedulers, and distributed workloads\nPartner closely with ML, research, and platform teams to translate workload needs into practical infrastructure improvements\nImprove provisioning, configuration management, testing, and deployment automation\nHelp plan cluster growth, capacity allocation, upgrades, and lifecycle management\nContribute to a thoughtful reliability culture through documentation, post-incident learning, and pragmatic engineering standards\nMinimum Qualifications\n4+ years of experience in site reliability engineering, infrastructure engineering, systems engineering, or a related production-operations role\nStrong hands-on expertise in at least one of the following:\nNetworking, including firewalls, switching, routing, ASN/BGP configuration, or InfiniBand\nCluster and systems allocation with Kubernetes, SLURM, MAAS, or similar platforms\nDistributed storage, particularly Ceph\nGPU and server administration, including CUDA drivers, firmware, BIOS, and hardware troubleshooting\nAI training or model-serving infrastructure\nExperience operating production systems with a focus on availability, performance, security, and automation\nStrong Linux administration and scripting skills\nA systematic approach to troubleshooting across multiple layers of a complex system\nClear written and verbal communication skills, including the ability to work effectively with a distributed team\nPreferred Qualifications\nExperience supporting GPU-intensive AI or HPC environments\n\nExperience with NVIDIA GPUs, CUDA, NCCL, and high-performance interconnects - Experience with InfiniBand, RDMA, RoCE, or 100Gb+ Ethernet\n\nFamiliarity with Kubernetes, SLURM, MAAS, Terraform, Ansible, or similar infrastructure tooling\n\nExperience operating or tuning Ceph clusters\n\nFamiliarity with observability tooling such as Prometheus, Grafana, and centralized logging systems\n\nExperience with hardware provisioning, firmware management, and bare-metal automation\n\nExperience running large-scale distributed training or high-throughput inference workloads\n\nFamiliarity with cloud and hybrid infrastructure across AWS, GCP, or Azure","description_format":"text","description_chars":3435,"description_truncated":false,"requirements":{"experience_years_min":4,"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":["Speech & Audio AI"],"lifecycle":[{"event":"open","at":"2026-09-11T10:36:39Z"}],"visa":[],"liveness":{"score":5,"band":"cold","label":"Long shot","p_open":1,"p_active":0.183,"p_room":0.28,"age_days":107,"expected_fill_days":29,"reasons":["conf:2","stale_co","ghost","win:tail","crowd:"],"computed_at":"2026-10-30T05:48:23Z"},"pay":{"stated_usd_annual":175444,"is_top_pay":true},"html_url":"https://alion.io/job/boson-site-reliability-engineer","json_url":"https://alion.io/job/boson-site-reliability-engineer.json","meta":{"generated_at":"2026-10-31T03:11:09Z","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":4464,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-01T00:00:00Z"}},"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":669673},"rest":"https://alion.io/mcp/rest/get_company?id=669673"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fboson-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%2Fboson-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%2Fboson-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/boson-site-reliability-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fboson-site-reliability-engineer"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":734436}},{"tool":"search_jobs","arguments":{"company":"boson.ai","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":734436},"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"}}