T-Hub - AIOps Engineer - AI Infrastructure & Orchestration

Location: Not specified

Contract: Employment contract. Working mode: Full time.

Company

hirify.global is a telecommunications company developing connectivity and technology solutions spanning 5G, IoT, and AI.

What you will do

• Design, deploy, and maintain vLLM inference services on OpenShift and Kubernetes running on bare-metal GPU infrastructure.
• Manage NVIDIA GPU partitioning and allocation across multiple models and tenants, optimizing utilization and serving performance.
• Automate model onboarding, versioning, deployment, hot-swapping, and rollback from private registries and S3.
• Build observability solutions with metrics, logging, tracing, Grafana dashboards, Prometheus, and Alertmanager.
• Implement usage tracking for token consumption, quota management, and chargeback or showback requirements.
• Provide API gateway, security, audit logging, incident response, root cause analysis, and continuous platform improvement in collaboration with AI, platform, security, and infrastructure teams.

Requirements

• 5+ years of experience in DevOps, SRE, platform engineering, or infrastructure operations.
• At least 2 years of hands-on experience with MLOps, AI infrastructure, or LLM platforms.
• Production experience administering Kubernetes and OpenShift and operating vLLM-based inference platforms.
• Knowledge of LLM serving concepts, including Paged Attention, continuous batching, and inference optimization.
• Experience with NVIDIA GPUs, CUDA drivers, NVIDIA Container Toolkit, GPU troubleshooting, Prometheus, Grafana, OpenTelemetry, and ELK Stack.
• Strong Python, Bash, and Linux administration skills, plus familiarity with GitLab CI, Jenkins, ArgoCD, and Infrastructure-as-Code practices.

Culture & Benefits

• Work with modern technologies including 5G, IoT, and AI.
• Collaborate across AI engineering, platform engineering, security, and infrastructure functions.
• Contribute to innovation in the telecommunications and connectivity domain.