Description
Mirantis is hiring a senior software engineer to build and operate an LLM serving layer on Kubernetes for its enterprise AI infrastructure product. The role owns deployment, GPU scheduling, scaling, model lifecycle management, Helm-based enterprise packaging, API gateway and identity integration, GPU inference observability, and engineering direction across a multi-service codebase. Candidates need at least five years of infrastructure, platform, or distributed systems experience, deep Kubernetes and Helm expertise, GPU or LLM inference experience, strong Go and CI/CD skills, and fluency with AI-assisted development tools.
