{"id":2131915,"url":"https://alion.io/job/apple-ml-infrastructure-engineer-ml-compute-capacity","title":"ML Infrastructure Engineer - ML Compute Capacity","company":{"id":12,"name":"Apple","domain":"apple.com","url":"https://alion.io/company/apple","size_band":"5000+","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Apple Jobs","truth_index":{"grade":"A","score":93,"open_postings":893,"ghost_share":0,"stale_share":0.075,"repost_share":0,"time_to_fill_p50_days":138,"computed_at":"2026-10-12T06:55:09Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"senior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Santa Clara, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":233000,"max_usd":444000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":1124},"experience_years_min":7,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"ElasticSearch","optional":false},{"name":"Go","optional":false},{"name":"Grafana","optional":false},{"name":"Machine Learning","optional":false},{"name":"PostgreSQL","optional":false},{"name":"Prometheus","optional":false},{"name":"Python","optional":false},{"name":"TPU","optional":false},{"name":"Trino","optional":false},{"name":"FinOps","optional":true},{"name":"Kubernetes","optional":true}],"status":"live","first_seen_at":"2026-09-11T18:50:52Z","employer_posted_date":"2026-10-09","last_verified_at":"2026-10-12T11:04:10Z","board_verified":true,"closed_at":null,"days_open":30,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":30},"description":"Scaling machine learning workloads across thousands of accelerators creates challenges that few engineers ever encounter. In Apple’s Machine Learning Platform Technologies organization, we build the infrastructure that powers large-scale ML training and inference workloads, bringing together expertise in distributed systems, machine learning infrastructure, and high-performance computing.\nDescription\nAs an engineer on the ML Compute Capacity team, you will design, build, and operate the production systems that ensure compute resources are optimally distributed throughout the company. You'll work across the stack - from data pipelines and backend services to APIs and interactive frontends - developing telemetry systems, optimization algorithms, policies, and intuitive tools for managing demand and improving efficiency across Apple's largest accelerator fleet. Our small, nimble team works in a high-autonomy, fast-paced environment, and we're passionate about digging into data patterns, laying out the performance characteristics of an entire distributed system, and knowledge sharing. If the opportunity to own and operate services that scale, stay highly available, and \"just work\" excites you, then please reach out to us!\nMinimum Qualifications\n7+ years of experience in relevant areas\nExperience with machine learning infrastructure on GPUs or TPUs\nProficiency in Python and/or Go for production backend and data engineering work\nExperience building data pipelines and crafting robust queries over large-scale, multi-source data (e.g., Trino, PostgreSQL, Elasticsearch)\nExperience with observability tools (e.g., Prometheus, Grafana) or equivalent monitoring systems\nExcellent problem-framing and problem-solving skills\nStrong CS fundamentals\nBachelor's degree or higher in Engineering, Mathematics, Economics, or a related quantitative field\nPreferred Qualifications\nExperience operating Kubernetes at production scale - including scheduling, resource management, and cluster debugging\nExperience with modern web frameworks like React\nFamiliarity with accelerator utilization patterns across ML training and inference\nStrong interest with capacity planning, cost attribution, or FinOps systems","description_format":"text","description_chars":2211,"description_truncated":false,"requirements":{"experience_years_min":7,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","Operating Systems","Smartwatches & Fitness Trackers","Tablets"],"lifecycle":[{"event":"open","at":"2026-10-09T01:09:42Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 6,350 · green card filings: 37","filings_12m":6350,"filings_prev_12m":6527,"green_card_filings_12m":37,"median_offered_wage_usd":177355,"route":null,"cap_exempt":false,"checked_at":"2026-10-03T21:08:04+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":2959}],"liveness":{"score":98,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.984,"p_room":1,"age_days":30,"expected_fill_days":138,"reasons":["conf:0","urgency","velocity","win:early","comp:brand"],"computed_at":"2026-10-12T06:55:09Z"},"pay":null,"html_url":"https://alion.io/job/apple-ml-infrastructure-engineer-ml-compute-capacity","json_url":"https://alion.io/job/apple-ml-infrastructure-engineer-ml-compute-capacity.json","meta":{"generated_at":"2026-10-12T17:08:38Z","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":27301,"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":12},"rest":"https://alion.io/mcp/rest/get_company?id=12"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fapple-ml-infrastructure-engineer-ml-compute-capacity"},{"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%2Fapple-ml-infrastructure-engineer-ml-compute-capacity"},{"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%2Fapple-ml-infrastructure-engineer-ml-compute-capacity"},{"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/apple-ml-infrastructure-engineer-ml-compute-capacity\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fapple-ml-infrastructure-engineer-ml-compute-capacity"}]}