{"id":2094996,"url":"https://alion.io/job/luma-ai-research-scientist-engineer-performance-optimization-2","title":"Research Scientist / Engineer – Performance Optimization","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":"remote","remote_scope":"unspecified","remote_scope_basis":"board_flag_no_place","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":[],"countries":[],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"Multimodal AI","optional":false},{"name":"PyTorch","optional":false},{"name":"Triton","optional":false},{"name":"ONNX","optional":true},{"name":"TensorRT","optional":true},{"name":"XLA","optional":true}],"status":"live","first_seen_at":"2026-10-08T15:04:03Z","employer_posted_date":"2026-10-08","last_verified_at":"2026-10-11T00:12:47Z","board_verified":true,"closed_at":null,"days_open":2,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":2},"description":"You'll make Luma's multimodal models fast - profiling and optimizing GPU, CPU, and accelerator code so they train efficiently and deploy at scale without sacrificing quality. You'll write the kernels and operations that get the most out of the hardware.\nThis is deep performance work: fused kernels, tensor cores, Triton and CUDA, distributed multi-node deployment. It fits someone with expert GPU-optimization skills and a deep understanding of transformer internals. If you're not at home in CUDA, Triton, and profilers, this is the wrong depth.\nWhat You'll Own\nProfile and optimize GPU/CPU/accelerator code for maximum utilization and minimal latency.\n\nWrite high-performance PyTorch, Triton, and CUDA, dropping to custom operations when needed.\n\nDevelop fused kernels and leverage tensor cores and modern hardware features across platforms.\n\nOptimize model architectures and implementations for distributed multi-node production deployment.\n\nBuild performance monitoring and analysis tools and automation.\n\nResearch and implement cutting-edge optimization techniques for transformer models.\n\nFirst 90 Days\nOne way the first 90 could unfold.\nDays 1-30 - Immerse & Diagnose: Profile the current training and inference paths and find the biggest performance wins.\n\nDays 30-60 - Ship & Validate: Land a kernel or architecture optimization that measurably improves utilization or latency.\n\nDays 60-90 - Scale & Systemize: Build the monitoring and automation that keeps performance gains from regressing.\n\nWhat You Bring\nExpert-level Triton/CUDA programming and GPU optimization.\n\nStrong PyTorch skills, including kernel development and custom operations.\n\nProficiency with profiling tools (NVIDIA Nsight, torch profiler, custom tooling).\n\nDeep understanding of transformer architectures and attention mechanisms.\n\nNice to Have\nExperience with compilers and exporters (torch.compile, TensorRT, ONNX, XLA).\n\nExperience optimizing inference workloads for latency and throughput.\n\nTriton compiler and kernel fusion techniques.\n\nKnowledge of warp-level intrinsics and advanced CUDA optimization.\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":2375,"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":["Generative 3D","Generative Image","Generative Video"],"lifecycle":[{"event":"open","at":"2026-10-08T16:25:30Z"}],"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":"2026-10-03T21:08:04+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)"],"filings_for_role_12m":0}],"liveness":{"score":90,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.903,"p_room":1,"age_days":1,"expected_fill_days":54,"reasons":["conf:1","velocity","win:early"],"computed_at":"2026-10-10T05:45:15Z"},"pay":null,"html_url":"https://alion.io/job/luma-ai-research-scientist-engineer-performance-optimization-2","json_url":"https://alion.io/job/luma-ai-research-scientist-engineer-performance-optimization-2.json","meta":{"generated_at":"2026-10-11T03:42:07Z","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","counted_by":"address","units_charged":1,"used_today":1641,"day_limit":5000,"remaining_today":3359,"minute_limit":60,"resets_at":"2026-10-12T00:00:00Z"}},"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-performance-optimization-2"},{"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-performance-optimization-2"},{"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-performance-optimization-2"},{"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-performance-optimization-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fluma-ai-research-scientist-engineer-performance-optimization-2"}]}