{"id":2131597,"url":"https://alion.io/job/apple-benchmarking-project-lead-siri-evaluation","title":"Benchmarking Project Lead, Siri Evaluation","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":"B","score":76,"open_postings":1017,"ghost_share":0,"stale_share":0.97,"repost_share":0,"time_to_fill_p50_days":36,"computed_at":"2026-10-13T05:45:00Z"}},"role":"Industrial Engineering","role_family":"Industrial Engineering","seniority":"lead","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Cambridge, United Kingdom"],"countries":["GB"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":113000,"max_usd":191000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":85},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Edge AI","optional":false}],"status":"live","first_seen_at":"2026-09-17T18:01:05Z","employer_posted_date":"2026-10-09","last_verified_at":"2026-10-13T11:27:37Z","board_verified":true,"closed_at":null,"days_open":25,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":25},"description":"Join the team redefining what a deeply personal and integrated assistant can be. As part of the Siri organization, you will help shape one of the world's most widely used AI assistants, powered by our next-generation of Apple Intelligence, with capabilities like personal context understanding and on-screen awareness, built with privacy from the ground up. Your work will have direct, meaningful impact for users across iOS, iPadOS, macOS, watchOS, and visionOS. This is a rare opportunity to build at the intersection of cutting-edge AI and human-centered design, shipping technology that is centered around users and their needs.\nEvaluation is at the heart of how we build our product. As Siri AI becomes more and more powerful and offers ever richer experiences to our users, our evaluations have to keep pace. We are seeking a senior manager to help drive our evaluation efforts. The role will involve managing teams working on evaluation development and data science, and leading high-impact initiatives to bring state-of-the-art agentic evaluation to the whole Siri team.","description_format":"text","description_chars":1078,"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":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Operating Systems","Laptops","Smartwatches & Fitness Trackers","Tablets"],"lifecycle":[{"event":"open","at":"2026-10-09T01:01:56Z"}],"visa":[{"country":"GB","licensed_sponsor":true,"evidence":"Licensed UK visa sponsor (Skilled Worker, Graduate Trainee, Senior or Specialist Worker)","filings_12m":null,"filings_prev_12m":null,"green_card_filings_12m":null,"median_offered_wage_usd":null,"route":"Skilled Worker; Global Business Mobility: Graduate Trainee; Global Business Mobility: Senior or Specialist Worker","cap_exempt":false,"checked_at":"2026-10-13T06:20:30+00:00","sources":["UK Home Office: register of licensed sponsors (workers)"],"filings_for_role_12m":0}],"liveness":{"score":45,"band":"ok","label":"Likely open","p_open":1,"p_active":0.601,"p_room":0.75,"age_days":25,"expected_fill_days":36,"reasons":["conf:1","stale_co","urgency","velocity","win:late","comp:brand"],"computed_at":"2026-10-13T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/apple-benchmarking-project-lead-siri-evaluation","json_url":"https://alion.io/job/apple-benchmarking-project-lead-siri-evaluation.json","meta":{"generated_at":"2026-10-13T13:33:14Z","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":20978,"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":12},"rest":"https://alion.io/mcp/rest/get_company?id=12"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fapple-benchmarking-project-lead-siri-evaluation"},{"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-benchmarking-project-lead-siri-evaluation"},{"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-benchmarking-project-lead-siri-evaluation"},{"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-benchmarking-project-lead-siri-evaluation\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fapple-benchmarking-project-lead-siri-evaluation"}]}