{"schemaVersion":"jobsearcher.job.v1","id":"4806bb1938077f684adc858a","url":"https://jobsearcher.com/jobs/4806bb1938077f684adc858a","canonicalUrl":"https://jobsearcher.com/jobs/4806bb1938077f684adc858a","title":"Staff ML Systems Engineer - Diffusion LLM Serving","description":"Inception is seeking engineers and scientists to design, optimize, and scale the diffusion LLM serving systems powering production inference. Your work will help make inference faster, more cost-efficient, and more reliable.\r\nYou will extend orchestration frameworks (Kubernetes, Ray, SLURM) for distributed inference, evaluation, and large-batch serving, and implement load balancing, autoscaling, and traffic routing for model endpoints.\r\nJ-18808-Ljbffr","company":"Inception","rawCompany":"inception","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-08-08T01:06:51.058Z","occupations":[{"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"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"}],"industries":[{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Staff ML Systems Engineer - Diffusion LLM Serving","description":"Inception is seeking engineers and scientists to design, optimize, and scale the diffusion LLM serving systems powering production inference. Your work will help make inference faster, more cost-efficient, and more reliable.\r\nYou will extend orchestration frameworks (Kubernetes, Ray, SLURM) for distributed inference, evaluation, and large-batch serving, and implement load balancing, autoscaling, and traffic routing for model endpoints.\r\nJ-18808-Ljbffr","datePosted":"2026-08-08T01:06:51.058Z","dateModified":"2026-08-08T01:06:51.058Z","hiringOrganization":{"@type":"Organization","name":"Inception","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"4806bb1938077f684adc858a"},"url":"https://jobsearcher.com/jobs/4806bb1938077f684adc858a"}}