{"id":42498,"url":"https://alion.io/job/zyphra-data-engineer-multimodal-systems","title":"Data Engineer - Multimodal Systems","company":{"id":8989,"name":"Zyphra","domain":"zyphra.com","url":"https://alion.io/company/zyphra","size_band":"1-10","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"D","score":48,"open_postings":16,"ghost_share":0.875,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-17T05:46:00Z"}},"role":"Data Science","role_family":"Data Science","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":133000,"max_usd":289000,"period":"year","method":"role_country_seniority_unknown","sample_n":3203},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Dask","optional":false},{"name":"Machine Learning","optional":false},{"name":"Multimodal AI","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false}],"status":"live","first_seen_at":"2026-03-17T03:54:44Z","employer_posted_date":"2026-03-17","last_verified_at":"2026-10-17T22:11:36Z","board_verified":true,"closed_at":null,"days_open":214,"trust":{"level":"ghost","repost_count":0,"flags":["stale","company_stale"],"days_open":214},"description":"Zyphra is an artificial intelligence company based in San Francisco, California.\nThe Role:\nAs aData Engineer - Multimodal Systems, you will be a core contributor to creating, collecting, and improving Zyphra’s datasets and data pipelines across a variety of modalities. Your work will intersect with almost every team at Zyphra. You will be involved in collecting large-scale datasets and implementing and optimizing highly parallel data pipelines.\nYou’ll Work Across:\nLarge-scale data collection across a variety of modalities (text, audio, image)\n\nDesigning and working with highly efficient, parallelized data processing pipelines across modalities\n\nDesigning and running rigorous experimental ablations to demonstrate the impact of new data improvements\n\nWhat We're Looking For / Requirements:\nStrong implementation and prototyping ability\n\nCan take an idea from conception to experimentation quickly\n\nThe ability to work well with others in a high-paced research setting\n\nCan rapidly learn new fields and are excited to implement new ideas\n\nExcellent communication and collaboration skills, and can work effectively on both research and engineering implementation at scale.\n\nQualifications / Additional Skills:\nExperience collecting, handling, and processing large datasets\n\nExperience with parallel Python programming frameworks such as Dask\n\nUnderstanding of the state-of-the-art in dataset curation across modalities\n\nA generally meticulous nature and a strong interest in actually looking at data and sanity checking things\n\nStrong grasp of proper experimental methodology for running rigorous ablations and other hypothesis testing\n\nUnderstanding of and interest in large-scale, highly parallel data processing pipelines.\n\nProficiency with PyTorch and Python.\n\nExperience contributing to large pre-existing codebases and rapidly getting up to speed.\n\nPreviously published machine learning research in well-respected venues.\n\nPostgraduate degree in a scientific subject (Computer Science, EE/EECS, Mathematics, Physics, Machine Learning)\n\nWhy Work at Zyphra:\nOur research methodology is grounded in methodical, step-by-step approaches to ambitious goals. Both deep research and engineering excellence are equally valued\n\nWe strongly value new and crazy ideas and are very willing to bet big on new ideas\n\nWe move as quickly as we can; we aim to minimize the bar to impact as low as possible\n\nWe all enjoy what we do and love discussing AI\n\nBenefits and Perks:\nComprehensive medical, dental, vision, and FSA plans\n\nCompetitive compensation and 401(k) plan\n\nRelocation and immigration support on a case-by-case basis\n\nIn-office snacks and meals provided\n\nUnlimited PTO and company holidays\n\nIn-person team in San Francisco with a collaborative, high-energy environment","description_format":"text","description_chars":2775,"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":["Unlimited PTO"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":true,"industries":["Foundation Models","AI Research Labs"],"lifecycle":[{"event":"open","at":"2026-03-17T03:54:44Z"}],"visa":[],"liveness":{"score":3,"band":"cold","label":"Long shot","p_open":1,"p_active":0.096,"p_room":0.28,"age_days":214,"expected_fill_days":26,"reasons":["conf:3","stale_co","ghost","win:tail","crowd:"],"computed_at":"2026-10-17T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/zyphra-data-engineer-multimodal-systems","json_url":"https://alion.io/job/zyphra-data-engineer-multimodal-systems.json","meta":{"generated_at":"2026-10-18T00:44:39Z","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":1277,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-19T00:00:00Z"}},"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":8989},"rest":"https://alion.io/mcp/rest/get_company?id=8989"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fzyphra-data-engineer-multimodal-systems"},{"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%2Fzyphra-data-engineer-multimodal-systems"},{"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%2Fzyphra-data-engineer-multimodal-systems"},{"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/zyphra-data-engineer-multimodal-systems\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fzyphra-data-engineer-multimodal-systems"}]}