{"schemaVersion":"jobsearcher.job.v1","id":"22e7fe1db64baeb20a21bc25","url":"https://jobsearcher.com/jobs/22e7fe1db64baeb20a21bc25","canonicalUrl":"https://jobsearcher.com/jobs/22e7fe1db64baeb20a21bc25","title":"Staff Software Engineer, ML Performance, GPU","description":"OverviewIn this role you will optimize and scale ML training and serving on Google's GPU infrastructure. You'll partner with product teams to onboard and optimize LLMs, run architecture simulations, and drive performance across fleets. You will identify bottlenecks, implement efficiency techniques, and guide hardware-aware stack improvements. This is a hands-on position focused on delivering high-performance ML workloads at scale with a strong emphasis on collaboration and impact.Compensation / Benefitsbonus targetequitybenefitscompetitive compensationcareer growth opportunitiesflexible work arrangementsResponsibilitiesIdentify performance opportunities for LLM training and serving and drive XLA:GPU/Triton optimizationsOnboard, optimize, and scale LLMs and ML models on GPU hardware with product teamsConduct architecture-level simulations, benchmarking, and roofline analyses to inform system designAnalyze fleet-wide performance and efficiency, pinpoint bottlenecks, and engineer scalable optimizationsResearch and implement model/data efficiency techniques, tooling, and profiling mechanisms to improve workload performance and training efficiencyKey requirementsBachelor's degree or equivalent practical experience8 years of software development experience5 years in ML design and ML infrastructure (deployment, evaluation, data processing, debugging, fine tuning)Experience with modern GPU architectures, memory hierarchies, and performance bottlenecksExperience with low-level GPU programming (CUDA, Triton, CUTLASS) and performance engineeringExperience with modern LLMs and deployment on AI acceleratorscross-functional collaborationleadership in project teamsability to work in a matrixed organizationCUDATritonCUTLASS","company":"Google","rawCompany":"google","city":"San Jose","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-10-26T13:43:58.780Z","occupations":[{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"}],"industries":[{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Staff Software Engineer, ML Performance, GPU","description":"OverviewIn this role you will optimize and scale ML training and serving on Google's GPU infrastructure. You'll partner with product teams to onboard and optimize LLMs, run architecture simulations, and drive performance across fleets. You will identify bottlenecks, implement efficiency techniques, and guide hardware-aware stack improvements. This is a hands-on position focused on delivering high-performance ML workloads at scale with a strong emphasis on collaboration and impact.Compensation / Benefitsbonus targetequitybenefitscompetitive compensationcareer growth opportunitiesflexible work arrangementsResponsibilitiesIdentify performance opportunities for LLM training and serving and drive XLA:GPU/Triton optimizationsOnboard, optimize, and scale LLMs and ML models on GPU hardware with product teamsConduct architecture-level simulations, benchmarking, and roofline analyses to inform system designAnalyze fleet-wide performance and efficiency, pinpoint bottlenecks, and engineer scalable optimizationsResearch and implement model/data efficiency techniques, tooling, and profiling mechanisms to improve workload performance and training efficiencyKey requirementsBachelor's degree or equivalent practical experience8 years of software development experience5 years in ML design and ML infrastructure (deployment, evaluation, data processing, debugging, fine tuning)Experience with modern GPU architectures, memory hierarchies, and performance bottlenecksExperience with low-level GPU programming (CUDA, Triton, CUTLASS) and performance engineeringExperience with modern LLMs and deployment on AI acceleratorscross-functional collaborationleadership in project teamsability to work in a matrixed organizationCUDATritonCUTLASS","datePosted":"2026-10-26T13:43:58.780Z","dateModified":"2026-10-26T13:43:58.780Z","hiringOrganization":{"@type":"Organization","name":"Google","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Jose","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"22e7fe1db64baeb20a21bc25"},"url":"https://jobsearcher.com/jobs/22e7fe1db64baeb20a21bc25"}}