{"id":35016,"url":"https://alion.io/job/luma-ai-research-scientist-engineer-training-infrastructure","title":"Research Scientist / Engineer – Training 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":"Data Science","role_family":"Data Science","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","New York, United States","Seattle, United States","London, United Kingdom"],"countries":["US","GB"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":195000,"max":395000,"currency":"USD","period":"year","gross":null,"usd_annual":395000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"CUDA","optional":false},{"name":"FSDP","optional":false},{"name":"MPI","optional":false},{"name":"Multimodal AI","optional":false},{"name":"NCCL","optional":false},{"name":"PyTorch","optional":false},{"name":"C","optional":true},{"name":"Linux","optional":true}],"status":"live","first_seen_at":"2026-07-24T21:55:51Z","employer_posted_date":"2026-10-08","last_verified_at":"2026-10-24T21:33:21Z","board_verified":true,"closed_at":null,"days_open":92,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":92},"description":"You'll build the distributed systems that train Luma's large-scale multimodal models across thousands of GPUs, so researchers can focus on innovation on top of reliable, efficient, scalable infrastructure.\nThis is hard PyTorch, CUDA, and distributed-systems work - advanced parallelism, training stability, and utilization across massive clusters. It fits an engineer who's solved real problems training foundation models at scale. If you haven't worked at the level of FSDP and multi-node training, this is the wrong depth.\nWhat You'll Own\nDesign, implement, and optimize efficient distributed training systems for models across thousands of GPUs.\n\nResearch and implement advanced parallelization (FSDP, Tensor Parallel, Pipeline Parallel, Expert Parallel).\n\nBuild monitoring, visualization, and debugging tools for large-scale training runs.\n\nOptimize training stability, convergence, and resource utilization across massive clusters.\n\nFirst 90 Days\nOne way the first 90 could unfold.\nDays 1-30 - Immerse & Diagnose: Learn the current training stack and where stability and utilization hurt at scale.\n\nDays 30-60 - Ship & Validate: Land a parallelization or stability improvement that measurably helps a real training run.\n\nDays 60-90 - Scale & Systemize: Build the monitoring and tooling that keeps large runs reliable and efficient.\n\nWhat You Bring\nExtensive distributed PyTorch training and parallelisms in foundation-model training.\n\nDeep understanding of GPU clusters, networking, and storage systems.\n\nFamiliarity with communication libraries (NCCL, MPI) and distributed-system optimization.\n\nNice to Have\nStrong Linux systems administration and scripting.\n\nExperience managing training runs across 100+ GPUs.\n\nExperience with containerization, orchestration, and cloud infrastructure.\n\nAbout Luma: Luma's mission is to build unified general intelligence that can generate, understand, and operate in the physical world. We believe multimodality is critical for intelligence - the next step beyond language models comes from vision. Luma is an equal opportunity employer.","description_format":"text","description_chars":2079,"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"},{"name":"United Kingdom","iso":"GB","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Generative 3D","Generative Image","Generative Video"],"lifecycle":[{"event":"open","at":"2026-07-24T21:55:51Z"}],"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":0}],"liveness":{"score":22,"band":"cold","label":"Long shot","p_open":1,"p_active":0.6,"p_room":0.36,"age_days":91,"expected_fill_days":57,"reasons":["conf:4","wave","velocity","win:tail","crowd:"],"computed_at":"2026-10-24T06:02:35Z"},"pay":{"stated_usd_annual":395000,"is_top_pay":true},"html_url":"https://alion.io/job/luma-ai-research-scientist-engineer-training-infrastructure","json_url":"https://alion.io/job/luma-ai-research-scientist-engineer-training-infrastructure.json","meta":{"generated_at":"2026-10-24T22:51:13Z","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":33501,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-25T00:00:00Z"}},"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-research-scientist-engineer-training-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-research-scientist-engineer-training-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-research-scientist-engineer-training-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-research-scientist-engineer-training-infrastructure\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fluma-ai-research-scientist-engineer-training-infrastructure"}]}