{"id":2797648,"url":"https://alion.io/job/modular-backend-engineer-multi-cloud-inference-platform","title":"Backend Engineer (Multi-cloud Inference Platform)","company":{"id":12469,"name":"Modular","domain":"modular.com","url":"https://alion.io/company/modular","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Welcome to the Jungle","truth_index":null},"role":"Backend","role_family":"Backend","seniority":"senior","employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":167000,"max":286000,"currency":"USD","period":"year","gross":null,"usd_annual":286000},"salary_estimate":null,"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"Azure","optional":false},{"name":"GCP","optional":false},{"name":"Kubernetes","optional":false},{"name":"LLM","optional":false},{"name":"Machine Learning","optional":false}],"status":"live","first_seen_at":"2026-10-18T00:11:13Z","employer_posted_date":"2026-10-18","last_verified_at":"2026-10-21T07:54:40Z","board_verified":true,"closed_at":null,"days_open":3,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":3},"description":"Join our Cloud Inference team as a Backend Engineer, where you'll be responsible for building a multi-cloud, multi-tenant platform for managing distributed LLM inference deployments. You'll work on optimizing performance, scalability, and observability while creating simple and effective deployment solutions. Enjoy a range of benefits, including health insurance, a 401k plan, a generous work-from-home stipend, and unlimited paid time off.\nMissions\nConcevoir et construire une plateforme multi-cloud et multi-locataire pour les services d'inférence.\nDévelopper des services tolérants aux pannes et à faible effort, capables d'utiliser des ressources sur diverses plateformes matérielles.\nAméliorer l'excellence opérationnelle avec une observabilité de la demande au noyau, des déploiements multi-cloud, et des optimisations de démarrage à froid.\nProfil recherché\n - We're seeking engineers who are passionate about pushing the boundaries of distributed inference systems and enjoy working at the intersection of large-scale systems and machine learning- We are looking for candidates based on their breadth and depth of experience in backend engineering, AI inference, and distributed systems development. If this sounds exciting, we invite you to join our world-leading AI infrastructure team and help drive our industry forward\n- Experience with kubernetes and operating your own services\n- 5+ years of experience working in backend engineering\n- A passion for building and operating high performance, low toil, observable systems\n- Creativity and curiosity for solving complex problems, a team-oriented attitude that enables you to work well with others, and alignment with our culture\n- Strongly identifies with our core company cultural values\n- Experience with Cloud Providers (AWS, GCP, Azure, neoclouds)\n- Experience in machine learning technologies and use cases\n- Practical experience implementing & maintaining security in multi-tenancy environments\n- Experience working on high scale ML inference infrastructure (traditional AI or genAI)\n- Familiarity with golang","description_format":"text","description_chars":2078,"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":["401k plan","Health insurance"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["AI Compute & Inference","AI Development Tools"],"lifecycle":[{"event":"open","at":"2026-10-18T00:38:54Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 16 · green card filings: 1","filings_12m":16,"filings_prev_12m":11,"green_card_filings_12m":1,"median_offered_wage_usd":220147,"route":null,"cap_exempt":false,"checked_at":"2026-10-15T11:24:14+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)","US Department of Labor: PERM disclosure data (green cards)"],"filings_for_role_12m":10}],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":3,"expected_fill_days":37,"reasons":["conf:2","win:early"],"computed_at":"2026-10-21T05:46:15Z"},"pay":{"stated_usd_annual":286000,"is_top_pay":true},"html_url":"https://alion.io/job/modular-backend-engineer-multi-cloud-inference-platform","json_url":"https://alion.io/job/modular-backend-engineer-multi-cloud-inference-platform.json","meta":{"generated_at":"2026-10-21T08:25:18Z","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":11932,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-22T00:00:00Z"}},"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":12469},"rest":"https://alion.io/mcp/rest/get_company?id=12469"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fmodular-backend-engineer-multi-cloud-inference-platform"},{"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%2Fmodular-backend-engineer-multi-cloud-inference-platform"},{"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%2Fmodular-backend-engineer-multi-cloud-inference-platform"},{"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/modular-backend-engineer-multi-cloud-inference-platform\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fmodular-backend-engineer-multi-cloud-inference-platform"}]}