AIOps Engineer - AI Infrastructure, GPUs, & Observability

Diverse Consulting Group; Polska; Hybrid; PLN 260,000 - 380,000; Full time

Benefits offered by this job

Private medical care

Co-financing for sports card

Training & learning opportunities

Dedicated consultant support

Job summary

Diverse Consulting Group is hiring for a DevOps/SRE role focused on AI infrastructure and MLOps. You will design and operate vLLM inference services on OpenShift/Kubernetes running on bare-metal GPUs, manage NVIDIA resources, and automate model lifecycles from onboarding to rollback.

Strong observability, CI/CD, and security practices are essential. The role requires deep expertise in Kubernetes/OpenShift, GPU tooling, and scalable infrastructure.

Qualifications

• 5+ years in DevOps, SRE, Platform Engineering, or Infra Operations.
• 2+ years supporting MLOps, AI infra, or LLM platforms.
• Production experience with Kubernetes/OpenShift.
• Experience deploying vLLM-based inference platforms.

Responsibilities

• Design, deploy, and maintain vLLM inference services on OpenShift/Kubernetes on GPU hardware.
• Manage NVIDIA GPU resources including partitioning and allocation.
• Automate model lifecycle management and deployment processes.
• Implement and optimize HPA based on workload and GPU usage.
• Build observability using metrics, logging, and tracing.
• Instrument endpoints to expose token, latency, and throughput metrics.
• Develop usage tracking for API keys, users, teams, or departments.
• Create Grafana dashboards for infrastructure and consumption metrics.
• Configure Prometheus and Alertmanager for proactive monitoring and alerts.
• Implement API Gateway for auth, rate limiting, and routing.
• Ensure secure operation through network segmentation and secure practices.
• Maintain audit logging for compliance and governance.
• Collaborate with AI/Platform/Security/Infra teams for reliable services.
• Participate in troubleshooting, incident response, and platform improvements.

Skills

Kubernetes

OpenShift

GPU management

Python

Prometheus

Grafana

OpenTelemetry

ELK Stack

GitLab CI

Jenkins

ArgoCD

IaC

Linux admin

Bash scripting

MLOps

Tools

OpenShift

Kubernetes

NVIDIA GPU tech

Job description

Diverse Consulting Group is hiring for a DevOps/SRE role focused on AI infrastructure and MLOps. You will design and operate vLLM inference services on OpenShift/Kubernetes running on bare-metal GPUs, manage NVIDIA resources, and automate model lifecycles from onboarding to rollback.

Strong observability, CI/CD, and security practices are essential. The role requires deep expertise in Kubernetes/OpenShift, GPU tooling, and scalable infrastructure.