{"schemaVersion":"jobsearcher.job.v1","id":"0e98643024403103ecb5cf5e","url":"https://jobsearcher.com/jobs/0e98643024403103ecb5cf5e","canonicalUrl":"https://jobsearcher.com/jobs/0e98643024403103ecb5cf5e","title":"LLMOps Platform Engineer for GPU AI Inference","description":"A leading AI infrastructure company located in New Jersey is seeking an experienced AI Operations Platform Consultant to lead and optimize large-scale GPU-accelerated AI platforms. The ideal candidate will have a strong background in deploying and managing LLM inference systems on Kubernetes, with expertise in TensorRT-LLM and Triton Inference Server. Responsibilities include managing production-grade LLM pipelines and ensuring operational reliability. This position is part of a team committed to diversity and equal opportunity. #J-18808-Ljbffr","company":"Cloud Analytics Technologies","rawCompany":"cloud analytics technologies","city":"Jersey City","state":"NJ","isRemote":false,"isActive":false,"createdAt":"2026-08-08T03:59:56.123Z","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":"11-3021.00","title":"Computer and Information Systems Managers","slug":"computer-and-information-systems-managers"}],"industries":[{"code":"518210","title":"Computing Infrastructure Providers, Data Processing, Web Hosting, and Related Services","slug":"computing-infrastructure-providers-data-processing-web-hosting-and-related-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":"LLMOps Platform Engineer for GPU AI Inference","description":"A leading AI infrastructure company located in New Jersey is seeking an experienced AI Operations Platform Consultant to lead and optimize large-scale GPU-accelerated AI platforms. The ideal candidate will have a strong background in deploying and managing LLM inference systems on Kubernetes, with expertise in TensorRT-LLM and Triton Inference Server. Responsibilities include managing production-grade LLM pipelines and ensuring operational reliability. This position is part of a team committed to diversity and equal opportunity. #J-18808-Ljbffr","datePosted":"2026-08-08T03:59:56.123Z","dateModified":"2026-08-08T03:59:56.123Z","hiringOrganization":{"@type":"Organization","name":"Cloud Analytics Technologies","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Jersey City","addressRegion":"NJ","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"0e98643024403103ecb5cf5e"},"url":"https://jobsearcher.com/jobs/0e98643024403103ecb5cf5e"}}