{"schemaVersion":"jobsearcher.job.v1","id":"5f4fd1e3837bfd83e1e2aedc","url":"https://jobsearcher.com/jobs/5f4fd1e3837bfd83e1e2aedc","canonicalUrl":"https://jobsearcher.com/jobs/5f4fd1e3837bfd83e1e2aedc","title":"Senior Backend Engineer, LLM Inference Systems","description":"Inception in San Francisco is seeking experienced backend engineers to own the systems that serve our diffusion LLMs in production. You will build and operate infrastructure that handles billions of inference requests, optimizing for latency, throughput, cost, and reliability.\r\nThis role sits at the intersection of ML systems and backend infrastructure, with responsibilities spanning scalable services, model serving, load balancing, canary deployments, and observability tooling to ensure SLA\r\nJ-18808-Ljbffr","company":"Inception","rawCompany":"inception","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-08-13T01:55:10.766Z","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":"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":"Senior Backend Engineer, LLM Inference Systems","description":"Inception in San Francisco is seeking experienced backend engineers to own the systems that serve our diffusion LLMs in production. You will build and operate infrastructure that handles billions of inference requests, optimizing for latency, throughput, cost, and reliability.\r\nThis role sits at the intersection of ML systems and backend infrastructure, with responsibilities spanning scalable services, model serving, load balancing, canary deployments, and observability tooling to ensure SLA\r\nJ-18808-Ljbffr","datePosted":"2026-08-13T01:55:10.766Z","dateModified":"2026-08-13T01:55:10.766Z","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":"5f4fd1e3837bfd83e1e2aedc"},"url":"https://jobsearcher.com/jobs/5f4fd1e3837bfd83e1e2aedc"}}