{"id":37792,"url":"https://alion.io/job/pragmatike-cuda-kernel-engineer-remote-us","title":"CUDA Kernel Engineer (Remote US)","company":{"id":8591,"name":"Pragmatike","domain":"pragmatike.com","url":"https://alion.io/company/pragmatike","size_band":"51-200","is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":75,"open_postings":5,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":41,"computed_at":"2026-09-29T05:45:00Z"}},"role":"Hardware","role_family":"Hardware","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"explicit","locations":["Cambridge, United States","San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":159000,"max_usd":364000,"period":"year","method":"role_country_seniority_unknown","sample_n":1828},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":true,"technologies":[{"name":"C++","optional":false},{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"CoreWeave","optional":true},{"name":"CUTLASS","optional":true},{"name":"Databricks","optional":true},{"name":"HPC","optional":true},{"name":"NCCL","optional":true},{"name":"NVLink","optional":true},{"name":"Sass","optional":true},{"name":"TensorRT","optional":true},{"name":"Weights & Biases","optional":true}],"status":"live","first_seen_at":"2026-04-22T14:45:00Z","employer_posted_date":"2026-04-22","last_verified_at":"2026-09-29T19:41:29Z","board_verified":true,"closed_at":null,"days_open":160,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":159},"description":"Location: SF on-site\nStart date: ASAP\nLanguages: English (required)\nAbout the Role\nPragmatike is hiring on behalf of a fast-growing AI startup recognized as a Top 10 GenAI company by GTM Capital, founded by MIT CSAIL researchers.\nWe are searching for a CUDA Kernel Engineer who has hands-on experience developing and optimizing NVIDIA CUDA kernels from scratch. You will work on the GPU performance layer powering large-scale, high-throughput AI systems used by Fortune 500 customers.\nThis role is ideal for someone who deeply understands NVIDIA GPU architecture, memory hierarchy, warp-level execution, and profiling workflows not someone coming from generic hardware, FPGA, or non-NVIDIA compute backgrounds. You will directly influence the GPU efficiency, throughput, and scalability of mission-critical AI systems.\nWhat Youll Do\nDesign, implement, and optimize custom CUDA kernels for NVIDIA GPUs, with a focus on maximizing occupancy, memory throughput, and warp efficiency.\n\nProfile GPU workloads using tools such as Nsight Compute, Nsight Systems, nvprof, and CUDA-MEMCHECK.\n\nAnalyze and eliminate performance bottlenecks including warp divergence, uncoalesced memory access, register pressure, and PCIe transfer overhead.\n\nImprove GPU memory pipelines (global, shared, L2, texture memory) and ensure proper memory coalescing.\n\nCollaborate closely with AI systems, model acceleration, and backend distributed systems teams.\n\nContribute to GPU architecture decisions, kernel libraries, and internal performance-engineering best practices.\n\nWhat Were Looking For\nProven track record building NVIDIA CUDA kernels from scratchnot just calling existing libraries.\n\nStrong ability to optimize kernels (tiling strategies, occupancy tuning, shared memory design, warp scheduling).\n\nDeep understanding of CUDA threads, warps, blocks, and grids, GPU memory hierarchy and memory coalescing, as well as warp divergence (how to detect, analyze, and mitigate it)\n\nExperience diagnosing PCIe bottlenecks and optimizing host-device transfers (pinned memory, streams, batching, overlap).\n\nFamiliarity with C++, CUDA runtime APIs, and GPU debugging/profiling tooling.\n\nBonus Points\nExperience with multi-GPU or distributed GPU systems (NCCL, NVLink, MIG).\n\nBackground in GPU acceleration for ML frameworks or HPC workloads.\n\nKnowledge of model inference optimization (TensorRT, CUDA Graphs, CUTLASS).\n\nExposure to compiler-level optimization or PTX/SASS analysis.\n\nStartup experience or comfort working in fast-moving, ambiguous environments.\n\nWhy This Role Will Pivot Your Career\nResearch pedigree: MIT CSAIL founders recognized for breakthrough AI and systems contributions.\n\nCustomer impact: Deploy AI solutions powering Fortune 500 clients.\n\nIndustry momentum: Lab alumni have led high-value acquisitions (MosaicML Databricks, Run:AI Nvidia, W&B CoreWeave).\n\nFunding & growth: Oversubscribed seed round, next funding in 2026.\n\nCareer growth & influence: Lead AI initiatives, optimize pipelines, and directly impact production AI systems at scale.\n\nCulture & autonomy: Own critical systems while collaborating with world-class engineers.\n\nAspirational impact: Solve GPU/AI performance challenges few engineers ever face.\n\nBenefits\nCompetitive salary & equity options\n\nSign-on bonus\n\nHealth, Dental, and Vision\n\n401k\n\n Pragmatike is an Equal Opportunity Employer and is committed to providing equal employment opportunities to all applicants without discrimination. We recruit on behalf of our clients and prohibit discrimination and harassment based on race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state, or local laws. This policy applies to all terms and conditions of employment, including recruiting, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation, and training.We are committed to a fair and inclusive hiring process. We process your personal data solely for recruitment purposes, in accordance with applicable privacy laws, and maintain reasonable safeguards to protect your information. Your data may be shared with our client(s) for hiring consideration, but will not be disclosed to third parties outside of the recruitment process.","description_format":"text","description_chars":4348,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"phd","optional":false},"security_clearance":false,"languages":[{"language":"English","level":"All levels","optional":false}]},"benefits":["401k plan","Equity"],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-04-22T14:45:00Z"}],"liveness":{"score":5,"band":"cold","label":"Long shot","p_open":1,"p_active":0.167,"p_room":0.28,"age_days":159,"expected_fill_days":41,"reasons":["conf:2","agency","velocity","win:tail","crowd:"],"computed_at":"2026-09-29T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/pragmatike-cuda-kernel-engineer-remote-us","json_url":"https://alion.io/job/pragmatike-cuda-kernel-engineer-remote-us.json","meta":{"generated_at":"2026-09-30T02:42:57Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":1924,"day_limit":5000,"remaining_today":3076,"minute_limit":60,"resets_at":"2026-10-01T00:00:00Z"}}}