Senior DevOps Engineer — Cybersecurity business unit
Core
Build and operate a cloud-native, AI-powered security platform with self-hosted LLM inference in air-gapped Kubernetes environments for global service provider networks.
Role type
Senior DevOps Engineer (Platform Engineering)
Builds
AI security platform, self-hosted LLM inference stack, and Kubernetes operator ecosystem
Domain
Cybersecurity, AI Infrastructure, Cloud-Native
Deliverable
production ML models
Required skills
Kubernetes, Helm, GitOps (ArgoCD/Flux), Infrastructure as Code, Stateful workloads on Kubernetes, Observability (Prometheus, Grafana, OpenTelemetry), Air-gapped environment operations
Preferred skills
OpenShift, KEDA, Temporal, AI inference infrastructure (vLLM, TGI, Triton), GPU scheduling, LLM gateways (LiteLLM), LLM observability (Langfuse)
Technologies
Kubernetes, Helm, ArgoCD, CloudNativePG, Strimzi, ECK, MinIO, Redis, Temporal, Grafana Alloy, OpenTelemetry, Prometheus, Kafka, Telepresence, mirrord, vLLM, TGI, Triton, LiteLLM, Langfuse
Responsibilities
Own Helm charts for portability across Kubernetes distributions; Operate self-hosted operator stack (CloudNativePG, Strimzi, ECK, MinIO, Redis, Temporal); Run Nx monorepo pipelines and drive ArgoCD GitOps rollouts; Implement zero-downtime releases via blue/green, canary, and automated rollback; Manage autoscaling, backup/restore, and load validation; Provide on-call support for dev/staging and customer stamps; Build observability dashboards and alerts; Improve developer experience with shared dev clusters and traffic interception
Seniority
Senior, hands-on IC