{"id":49885,"url":"https://alion.io/job/luma-ai-software-engineer-data-infrastructure","title":"Software Engineer - Data Infrastructure","company":{"id":247,"name":"Luma AI","domain":"lumalabs.ai","url":"https://alion.io/company/luma-ai","size_band":"201-500","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":null},"role":"Backend","role_family":"Backend","seniority":null,"employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Redwood City, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":170000,"max":360000,"currency":"USD","period":"year","gross":null,"usd_annual":360000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Machine Learning","optional":false},{"name":"Multimodal AI","optional":false},{"name":"Python","optional":false},{"name":"Ray","optional":false},{"name":"Spark","optional":false}],"status":"live","first_seen_at":"2026-08-10T20:35:01Z","employer_posted_date":"2026-08-10","last_verified_at":"2026-10-18T04:45:19Z","board_verified":true,"closed_at":null,"days_open":68,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":68},"description":"About the Role\nAs a Data Infrastructure Engineer in Research at Luma, you will play a critical role in building and scaling the data infrastructure that supports our cutting-edge multimodal AI systems. Your work will focus on developing high-throughput, large-scale data processing pipelines tailored for machine learning research and internal ML platform needs. You will collaborate closely with ML researchers and product teams to create reliable, efficient, and easy-to-use data infrastructure that empowers innovation and accelerates development. This role requires a strong foundation in distributed systems and data engineering, with an emphasis on supporting complex machine learning workflows rather than traditional product data infrastructure.\nResponsibilities\nBuild and maintain scalable data infrastructure for high-throughput machine learning workflows\n\nCollaborate with ML researchers and product teams to ensure data systems meet evolving needs\n\nDevelop and optimize large-scale data pipelines and batch processing jobs\n\nContribute to the architecture and implementation of reliable, high-performance data platforms\n\nIntegrate open-source tools and continuously improve data infrastructure through monitoring and tuning\n\nParticipate in cross-functional projects to improve data reliability, scalability, and operational excellence\n\nSupport the evaluation and adoption of new programming languages and frameworks relevant to data infrastructure\n\nEngage in continuous improvement of data infrastructure through monitoring, troubleshooting, and performance tuning\n\nCollaborate with research & engineering teams to help define and refine best practices for data infrastructure development\n\nQualifications\nProficiency in Python (or similar languages with willingness to learn Python) and experience with large-scale, high-throughput data infrastructure\n\nFamiliarity with distributed computing frameworks (e.g., Ray, Spark, Beam)\n\nAbility to design and optimize data pipelines for ML research and internal teams\n\nStrong problem-solving skills and understanding of data engineering at scale\n\nCollaborative, product-focused mindset; comfortable in fast-paced environments\n\nExperience sourcing, integrating, and optimizing data from diverse and large datasets\n\nComfortable working in a fast-paced, product-focused environment with a strong execution mindset\n\nOpen to candidates across seniority levels, from mid-level individual contributors to senior engineers and managers.\n\nNice to have\nPrior experience working with complex data infrastructure or AI/ML platforms highly desirable\n\nExperience with open source data infrastructure projects is a plus\n\nExperience working in the robotics industry preferred","description_format":"text","description_chars":2712,"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":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Generative 3D","Generative Image","Generative Video"],"lifecycle":[{"event":"open","at":"2026-08-10T20:35:01Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 37","filings_12m":37,"filings_prev_12m":9,"green_card_filings_12m":0,"median_offered_wage_usd":183446,"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)"],"filings_for_role_12m":10}],"liveness":{"score":23,"band":"cold","label":"Long shot","p_open":1,"p_active":0.53,"p_room":0.44,"age_days":67,"expected_fill_days":54,"reasons":["conf:3","velocity","win:tail","crowd:"],"computed_at":"2026-10-17T05:46:00Z"},"pay":{"stated_usd_annual":360000,"is_top_pay":true},"html_url":"https://alion.io/job/luma-ai-software-engineer-data-infrastructure","json_url":"https://alion.io/job/luma-ai-software-engineer-data-infrastructure.json","meta":{"generated_at":"2026-10-18T07:04:26Z","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":10523,"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":247},"rest":"https://alion.io/mcp/rest/get_company?id=247"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fluma-ai-software-engineer-data-infrastructure"},{"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%2Fluma-ai-software-engineer-data-infrastructure"},{"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%2Fluma-ai-software-engineer-data-infrastructure"},{"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/luma-ai-software-engineer-data-infrastructure\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fluma-ai-software-engineer-data-infrastructure"}]}