GPU-Infra DevOps Engineer | Linux, Kubernetes, CUDA, vLLM
Listed on 2026-11-01
-
IT/Tech
SRE/Site Reliability, Cloud Computing: Infrastructure & Operations, Unix/Linux, IT Infrastructure
N/A NDA ищет специалиста по GPU-инфраструктуре для подготовки и эксплуатации окружения под AI/ML. Кандидат будет работать с Ubuntu Server, Docker, Kubernetes и NVIDIA GPU, настраивая комплекс инфраструктуры для развёртывания vLLM и сопутствующих решений.
Требуется опыт работы с Prometheus, Grafana, TLS, DNS, Bash, Terraform и Ansible; плюсом станет опыт bare-metal Kubernetes, GDPR, репродуцируемые развёртывания и перенос приложений между облаком и локальной инфраструктурой.
The following role is for a GPU-Infra Dev Ops Engineer | Linux, Kubernetes, CUDA, vLLM with NDA.
Our group is growing, and we are hiring a GPU-Infra Dev Ops Engineer | Linux, Kubernetes, CUDA, vLLM in United States.
This role is for the GPU-Infra Dev Ops Engineer | Linux, Kubernetes, CUDA, vLLM role at NDA.
We are seeking a motivated GPU-Infra Dev Ops Engineer | Linux, Kubernetes, CUDA, vLLM to join NDA in United States.
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).