Senior DevOps Engineer
Posted Updated
Description
Casado is seeking a DevOps/SRE Engineer to strengthen the team and scale a microservices platform across AWS, GCP and on‑prem environments. You will build, deploy and operate Kubernetes clusters, and maintain GPU‑enabled ML inference services.
We value 5+ years in DevOps/SRE, Linux mastery, Terraform/Ansible/Python, and a strong GitOps approach, with a track record of designing scalable, secure systems.
Deploy, operate and evolve microservices on Kubernetes across cloud and on‑prem (Rancher). Support GPU-based ML inference services (TRITON, vLLM) on RunPod/Scaleway/Nebius. Build and maintain Docker images; ensure stable service lifecycle. Scale Kubernetes clusters and participate in incident response and performance tuning. Develop and evolve custom Helm charts for services. Design CI/CD pipelines with GitHub and GitLab for on‑prem deployments. Ensure SOC 2 compliance and improve security processes. Manage cluster access via VPN with RBAC and group policies. IaC-driven infrastructure using Terraform and Ansible. Develop observability with Grafana/Prometheus and ELK/Log storage. Minimum 5 years in DevOps and/or SRE roles. Strong Linux system administration experience. Extensive Kubernetes deployment, operation and scaling experience. Deep cloud provider expertise (preferably GCP, AWS acceptable). Experience with ML inference on GPU/CPU is a plus. Proven SRE practices and observability stack knowledge (Grafana/Prometheus/Loki). Strong GitOps, IaC and CI/CD fundamentals. Advanced Terraform, Ansible and Python skills. Ability to learn quickly in a high-uncertainty product environment. Proactive debugging and strategic technology choices for long-term goals. Fully remote 21 vacation days + public holidays + 5 Private English lessons via PreplySkills
Sign in to read and join the discussion.