{"schemaVersion":"jobsearcher.job.v1","id":"54f2374139ea2d99e3229848","url":"https://jobsearcher.com/jobs/54f2374139ea2d99e3229848","canonicalUrl":"https://jobsearcher.com/jobs/54f2374139ea2d99e3229848","title":"Machine Learning Engineer, GPU Performance","description":"Brahma is conducting this search on behalf of a client.\r\nWe're a small, well-funded founding team rebuilding the training and inference stack for generative video and image models. Today's stack was built for language models. We're co-designing across GPU kernels, distributed systems, and the models themselves to make these workloads dramatically faster and cheaper. Our inference engine is live with customers in generative media and robotics.\r\nThis is an early engineering hire. You'll report directly to the CEO and work alongside a founding team with deep expertise in distributed systems, kernel optimization, cloud infrastructure, and ML research.\r\nWhat you'll doOptimize GPU performance for training and inference on image and video generation workloads\r\nProfile and remove bottlenecks at the kernel, memory, system, and cluster level using Nsight and related tools\r\nWrite CUDA and Triton kernels that ship to production\r\nBuild distributed inference and training engines for diffusion models across multiple GPUs and nodes\r\nOwn communication performance: NCCL, RDMA over InfiniBand or RoCE, and disaggregated serving\r\nBuild benchmarking and regression harnesses so performance gains hold in production\r\nWhat we're looking for1+ years working on deep learning inference or training systems, or distributed systems\r\nHands-on experience with CUDA, Triton, PyTorch internals, or GPU profiling\r\nStrong CS fundamentals and a drive to go deep on hard technical problems\r\nYou'd rather make a model ten times faster than train one#J-18808-Ljbffr","company":"Brahma Consulting Group","rawCompany":"brahma consulting group","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-10-04T02:16:51.473Z","occupations":[{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"}],"industries":[{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Machine Learning Engineer, GPU Performance","description":"Brahma is conducting this search on behalf of a client.\r\nWe're a small, well-funded founding team rebuilding the training and inference stack for generative video and image models. Today's stack was built for language models. We're co-designing across GPU kernels, distributed systems, and the models themselves to make these workloads dramatically faster and cheaper. Our inference engine is live with customers in generative media and robotics.\r\nThis is an early engineering hire. You'll report directly to the CEO and work alongside a founding team with deep expertise in distributed systems, kernel optimization, cloud infrastructure, and ML research.\r\nWhat you'll doOptimize GPU performance for training and inference on image and video generation workloads\r\nProfile and remove bottlenecks at the kernel, memory, system, and cluster level using Nsight and related tools\r\nWrite CUDA and Triton kernels that ship to production\r\nBuild distributed inference and training engines for diffusion models across multiple GPUs and nodes\r\nOwn communication performance: NCCL, RDMA over InfiniBand or RoCE, and disaggregated serving\r\nBuild benchmarking and regression harnesses so performance gains hold in production\r\nWhat we're looking for1+ years working on deep learning inference or training systems, or distributed systems\r\nHands-on experience with CUDA, Triton, PyTorch internals, or GPU profiling\r\nStrong CS fundamentals and a drive to go deep on hard technical problems\r\nYou'd rather make a model ten times faster than train one#J-18808-Ljbffr","datePosted":"2026-10-04T02:16:51.473Z","dateModified":"2026-10-04T02:16:51.473Z","hiringOrganization":{"@type":"Organization","name":"Brahma Consulting Group","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"54f2374139ea2d99e3229848"},"url":"https://jobsearcher.com/jobs/54f2374139ea2d99e3229848"}}