Source description
About the role
We're hiring: DevOps Engineer at Katonic AI (remote) At Katonic AI, we build a Kubernetes-native MLOps, LLMOps & AgentOps platform that helps enterprises build, deploy, serve, and govern AI/ML workloads and autonomous AI agents across cloud and on-premises (sovereign) environments, including production-grade, GPU-accelerated training and inference, retrieval-augmented knowledge, tool-using and multi-agent systems, and built-in evaluation and guardrails. We're looking for a hands-on DevOps Engineer (2+ years) to help operate and scale that infrastructure alongside our senior DevOps and platform engineers. What you'll work on: * Deploying and maintaining containerized apps on Kubernetes (RKE2 / managed clusters) * Building images with Docker and packaging apps with Helm * Improving CI/CD pipelines (GitHub Actions, ArgoCD) * Operating our observability stack (Prometheus, Grafana, Loki) * Writing automation in Python / Bash and troubleshooting networking, storage, and compute What we're looking for: * Solid Kubernetes and Docker fundamentals * Comfort in Linux and the command line * Familiarity with CI/CD and Git-based workflows * Bonus: exposure to Istio/NGINX Ingress, a cloud provider (Azure/GCP/AWS), Terraform/Ansible, or MLOps/LLMOps tooling (vLLM, MLflow, Kubeflow, Ray) If you're strong on cloud-native fundamentals and want to go deep on ML infrastructure with real ownership and mentorship, this is a strong growth role. Apply here: https://rb.gy/p0sj8l Please note: applications are reviewed only through the link above. Comments, DMs, or interested replies won't be considered; profiles that don't apply via the form won't be shortlisted.
More at Katonic.ai