Senior DevOps engineer to operate production Kubernetes platform for LLM workloads.
Own and operate a production-grade Kubernetes infrastructure serving large language model inference at scale, handling GPU-enabled nodes, cluster upgrades, and incident resolution. This is a hands-on individual contributor role based in Stockholm but fully remote, working with Talos Linux, NVIDIA technologies, and model-serving frameworks. You'll take end-to-end responsibility for platform reliability, security, and developer experience while collaborating with infrastructure and product teams. Requires deep production Kubernetes expertise, Linux administration, and strong troubleshooting skills; experience with GPU infrastructure and AI/ML platforms is preferred.
Membership is €29/month, cancel anytime: every rate, every original listing link, and a daily alert for roles matching your filters.
Found at a specialist agency · listed 13 October 2026 · InsideJobs links you to the original posting.