{"id":3036762,"url":"https://alion.io/job/apple-machine-learning-research-engineer-pretraining-data-foundation-models","title":"Machine Learning Research Engineer, Pretraining Data — Foundation Models","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":91,"open_postings":911,"ghost_share":0.001,"stale_share":0.151,"repost_share":0.003,"time_to_fill_p50_days":99,"computed_at":"2026-10-27T05:46:45Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Cupertino, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":225000,"max_usd":500000,"period":"year","method":"role_country_seniority_unknown","sample_n":4425},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Machine Learning","optional":false},{"name":"Python","optional":false},{"name":"LLM","optional":true},{"name":"PyTorch","optional":true},{"name":"Ray","optional":true},{"name":"Spark","optional":true},{"name":"Synthetic Data","optional":true}],"status":"live","first_seen_at":"2026-10-21T21:00:30Z","employer_posted_date":"2026-10-21","last_verified_at":"2026-10-27T21:57:30Z","board_verified":true,"closed_at":null,"days_open":6,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":6},"description":"Apple is revolutionizing artificial intelligence by developing sophisticated foundation models that power intelligent features across our product ecosystem. We're seeking skilled Machine Learning Engineers to transform cutting-edge research into scalable, production-ready AI solutions. We are looking for engineers who are passionate about building systems that push the frontier of deep learning in terms of scaling, efficiency, and flexibility and delight millions of users in Apple products.\nApple's Foundation Models team is building the next generation of large language models that power intelligent experiences across Apple products. High-quality, diverse, and scalable training data is fundamental to advancing model capabilities in knowledge, reasoning, coding, and multilingual understanding.\nWe are seeking talented and motivated Research Engineers to advance the state of the art in pretraining data research and engineering. In this role, you will develop novel algorithms and scalable systems for data curation, quality assessment, and optimization, working closely with model training researchers to translate innovative ideas into measurable improvements in foundation model capabilities.\nThis position offers a unique opportunity to work at the intersection of cutting-edge machine learning research and large-scale systems engineering, with direct impact on the development of next-generation foundation models.\nDescription\nAs a Research Engineer on the Pretraining Data team, you will own technically challenging projects spanning research, algorithm development, experimentation, and production engineering.\nYou will investigate new approaches to improving training data quality, diversity, and efficiency, while building robust and scalable infrastructure to support the processing of massive datasets. You will collaborate closely with model training teams to understand the relationship between data and model capabilities, design controlled experiments, and continuously improve pretraining strategies.\nMinimum Qualifications\nBS, MS, or PhD in Computer Science, Machine Learning, or a related technical field, or equivalent practical experience.\nStrong programming skills in Python and proficiency in developing production-quality software.\nExperience with large-scale data processing, distributed computing, or machine learning systems.\nSolid understanding of machine learning fundamentals and modern deep learning architectures.\nStrong analytical and problem-solving skills, with the ability to independently investigate complex technical challenges.\nPreferred Qualifications\nExperience with LLM pretraining, training data research, or foundation model development.\nExperience designing and implementing scalable data processing pipelines using Spark, Ray, or similar distributed computing frameworks.\nHands-on experience with PyTorch, model training, and experimental evaluation.\nFamiliarity with data filtering, deduplication, data mixture optimization, and learned data quality signals.\nUnderstanding of scaling laws, training dynamics, and the relationship between data and model performance.\nExperience with synthetic data generation, data selection, or model-based data evaluation.\nDemonstrated ability to translate research ideas into scalable production systems.\nPublications or meaningful contributions to machine learning research or open-source projects.","description_format":"text","description_chars":3392,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":true},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Operating Systems","Laptops","Smartwatches & Fitness Trackers","Tablets"],"lifecycle":[{"event":"open","at":"2026-10-21T21:32:47Z"}],"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":"2026-10-15T11:24:14+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":2959}],"liveness":{"score":99,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.993,"p_room":1,"age_days":5,"expected_fill_days":99,"reasons":["conf:2","urgency","velocity","win:early","comp:brand"],"computed_at":"2026-10-27T05:46:45Z"},"pay":null,"html_url":"https://alion.io/job/apple-machine-learning-research-engineer-pretraining-data-foundation-models","json_url":"https://alion.io/job/apple-machine-learning-research-engineer-pretraining-data-foundation-models.json","meta":{"generated_at":"2026-10-27T22:18:05Z","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":13924,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-28T00:00:00Z"}},"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-machine-learning-research-engineer-pretraining-data-foundation-models"},{"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-machine-learning-research-engineer-pretraining-data-foundation-models"},{"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-machine-learning-research-engineer-pretraining-data-foundation-models"},{"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-machine-learning-research-engineer-pretraining-data-foundation-models\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fapple-machine-learning-research-engineer-pretraining-data-foundation-models"}]}