{"id":936288,"url":"https://alion.io/job/anyone-ai-gpu-kernel-engineer-cuda-triton-accelerator-performance","title":"GPU Kernel Engineer – CUDA, Triton & Accelerator Performance","company":{"id":9137,"name":"Anyone AI","domain":"anyoneai.com","url":"https://alion.io/company/anyone-ai","size_band":"51-200","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"A","score":95,"open_postings":152,"ghost_share":0,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":63,"computed_at":"2026-11-03T05:54:40Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"middle","employment_type":"contractor","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":[],"countries":[],"hiring_countries":["AR","BR","CO","MX","ES","CL","EC","PT","UY"],"hiring_countries_total":9,"salary":{"min":65,"max":65,"currency":"USD","period":"hour","gross":null,"usd_annual":130000},"salary_estimate":null,"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AWS","optional":false},{"name":"CUDA","optional":false},{"name":"JAX","optional":false},{"name":"Triton","optional":false},{"name":"AWS Trainium","optional":true},{"name":"cuDNN","optional":true},{"name":"MLIR","optional":true},{"name":"RLHF","optional":true},{"name":"TPU","optional":true},{"name":"XLA","optional":true}],"status":"live","first_seen_at":"2026-09-15T14:14:39Z","employer_posted_date":"2026-09-15","last_verified_at":"2026-11-03T14:34:34Z","board_verified":true,"closed_at":null,"days_open":49,"trust":{"level":"ok","repost_count":0,"flags":[],"days_open":48},"description":"Anyone AI is recruiting experienced GPU Kernel Engineers for a specialized project focused on reviewing, debugging, and evaluating high-performance compute kernels used in AI workloads.\nWe’re looking for engineers with hands-on experience writing and optimizing kernels across frameworks such as CUDA, Triton, NKI, or Pallas, with a strong understanding of numerical correctness, GPU performance, memory optimization, and benchmarking.\nWhat You’ll Work On\nYou’ll work with GPU and accelerator kernel tasks involving:\nKernel implementation and debugging\n\nCUDA and Triton optimization\n\nTranslation between kernel frameworks\n\nHardware migration\n\nOperator fusion\n\nPerformance profiling and benchmarking\n\nNumerical correctness verification\n\nCompilation and runtime debugging\n\nMemory hierarchy optimization\n\nKernel-level AI workload performance\n\nYou’ll assess whether implementations are technically correct, efficiently designed, reproducible, and appropriately optimized for the target hardware.\nWhat We’re Looking For\n3+ years of hands-on experience developing, optimizing, or debugging GPU or accelerator kernels\n\nStrong experience with at least two of the following:\nCUDA\n\nTriton\n\nNKI / AWS Neuron\n\nPallas / JAX\n\nStrong understanding of GPU performance optimization\n\nExperience with kernel profiling tools such as Nsight, NCU, roofline analysis, or framework-native profilers\n\nUnderstanding of:\nMemory bandwidth\n\nCompute throughput\n\nGPU occupancy\n\nShared memory\n\nRegister pressure\n\nMemory coalescing\n\nBank conflicts\n\nStrong understanding of floating-point numerical correctness and tolerance thresholds\n\nExperience debugging kernel compilation and runtime issues\n\nAbility to distinguish software defects, environment problems, and genuine optimization challenges\n\nRelevant Experience\nCandidates should have experience with several of the following types of work:\nWriting kernels from technical specifications\n\nTranslating kernels between CUDA, Triton, or other frameworks\n\nMigrating kernels across hardware platforms\n\nDebugging incorrect kernel implementations\n\nOptimizing kernel performance\n\nFusing multiple operations into optimized kernels\n\nNice to Have\nExperience across both NVIDIA GPU and custom accelerator ecosystems\n\nExperience with AWS Trainium, TPU, JAX, or other accelerators\n\nCompiler engineering experience\n\nFamiliarity with MLIR, XLA, or intermediate representation lowering\n\nContributions to GPU or ML kernel libraries\n\nExperience with cuBLAS, cuDNN, Triton community kernels, or JAX/XLA custom calls\n\nExperience with AI model evaluation, RLHF, or technical benchmark development\n\nWhat You’ll Be Responsible For\nReviewing GPU and accelerator kernel implementations for correctness\n\nComparing outputs against reference implementations\n\nEvaluating numerical tolerance thresholds\n\nReviewing kernel benchmarks and determining whether comparisons are fair\n\nIdentifying performance bottlenecks and optimization opportunities\n\nAssessing whether performance targets are realistic given hardware limits\n\nReviewing kernel translations and hardware migrations\n\nIdentifying compilation, driver, memory, shape, and runtime issues\n\nDetermining whether technical tasks are genuinely difficult or incorrectly configured\n\nProviding clear, actionable technical feedback\n\nEngagement\nWork Type: Remote\nEngagement: Part-time, project-based consulting\nFocus: GPU kernels, performance engineering, debugging, and technical evaluation\nThis role is ideal for engineers who enjoy working close to the hardware, optimizing GPU workloads, debugging low-level performance issues, and pushing AI compute systems toward their performance limits.","description_format":"text","description_chars":3629,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"Argentina","iso":"AR","kind":"country"},{"name":"Brazil","iso":"BR","kind":"country"},{"name":"Colombia","iso":"CO","kind":"country"},{"name":"Mexico","iso":"MX","kind":"country"},{"name":"Spain","iso":"ES","kind":"country"},{"name":"Chile","iso":"CL","kind":"country"},{"name":"Ecuador","iso":"EC","kind":"country"},{"name":"Portugal","iso":"PT","kind":"country"},{"name":"Uruguay","iso":"UY","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Angel Networks & Startup Accelerators","Bootcamps","Recruiting & Staffing","AI Training Data & Annotation"],"lifecycle":[{"event":"open","at":"2026-09-15T14:47:54Z"}],"visa":[],"liveness":{"score":64,"band":"ok","label":"Likely open","p_open":1,"p_active":0.848,"p_room":0.75,"age_days":48,"expected_fill_days":63,"reasons":["conf:0","velocity","win:late","comp:brand"],"computed_at":"2026-11-03T05:54:40Z"},"pay":{"stated_usd_annual":130000,"is_top_pay":false},"html_url":"https://alion.io/job/anyone-ai-gpu-kernel-engineer-cuda-triton-accelerator-performance","json_url":"https://alion.io/job/anyone-ai-gpu-kernel-engineer-cuda-triton-accelerator-performance.json","meta":{"generated_at":"2026-11-03T18:53:41Z","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":883,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-04T00:00:00Z"}},"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":9137},"rest":"https://alion.io/mcp/rest/get_company?id=9137"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fanyone-ai-gpu-kernel-engineer-cuda-triton-accelerator-performance"},{"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%2Fanyone-ai-gpu-kernel-engineer-cuda-triton-accelerator-performance"},{"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%2Fanyone-ai-gpu-kernel-engineer-cuda-triton-accelerator-performance"},{"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/anyone-ai-gpu-kernel-engineer-cuda-triton-accelerator-performance\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fanyone-ai-gpu-kernel-engineer-cuda-triton-accelerator-performance"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":936288}},{"tool":"search_jobs","arguments":{"company":"anyoneai.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":936288},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}