AIOps Engineer: AI Infra & Orchestration (Remote)

Telekom; Województwo mazowieckie; Hybrid; PLN 180,000 - 260,000; Full time

Benefits offered by this job

Remote work options

Hybrid work model

Contract of Employment

Job summary

T-Hub Polska in Warsaw is seeking an AIOps Engineer to design, deploy, and maintain vLLM inference services on OpenShift/Kubernetes running on bare-metal GPU infrastructure. You will manage NVIDIA GPU resources to maximize usage across models and tenants.

The role focuses on automation, observability, and security, covering model lifecycle management, HPA, and monitoring dashboards in Grafana, with teams across AI and Platform collaborating. Remote/hybrid work options are available.

Qualifications

• 5+ years of experience in DevOps, SRE, Platform Engineering, or Infrastructure Operations.
• At least 2 years hands-on in supporting MLOps, AI infrastructure, or LLM platforms.
• Strong Kubernetes and OpenShift in production.
• Proven experience deploying vLLM-based inference platforms.
• Deep knowledge of NVIDIA GPU tech, CUDA drivers, NVIDIA Container Toolkit.
• Hands-on with Prometheus, Grafana, OpenTelemetry, and ELK Stack.
• Strong Python and automation tooling.
• Bash scripting and Linux systems administration.
• Familiarity with GitLab CI, Jenkins, ArgoCD, and Infrastructure-as-Code.
• Strong analytical and problem-solving skills.

Responsibilities

• Design, deploy, and maintain vLLM inference services on OpenShift/Kubernetes on bare-metal GPU.
• Manage NVIDIA GPU resources for multi-model/tenant workloads.
• Automate model lifecycle management with private registries.
• Implement and manage HPA based on workload and GPU usage.
• Optimize vLLM configurations for performance and resource efficiency.
• Build observability: metrics, logging, tracing.
• Instrument endpoints to expose token usage, latency, throughput, errors.
• Develop usage tracking for API keys, users, teams with quota management.
• Set up Prometheus/Alertmanager monitoring and dashboards.
• Implement API gateway with auth, rate limits, and intelligent routing.
• Ensure security, network segmentation, audit logging.
• Collaborate with AI, Platform, Security, and Infrastructure teams.
• Participate in troubleshooting, incident response, and continuous improvement.

Skills

Kubernetes

OpenShift

Python

Linux systems administration

Bash scripting

CI/CD automation

Observability

OpenTelemetry

Prometheus

Grafana

NVIDIA GPU tech

ELK Stack

ArgoCD

GitLab CI

Infrastructure as Code

Troubleshooting

Tools

NVIDIA Container Toolkit

CUDA drivers

OpenShift

Prometheus

Grafana

OpenTelemetry

ELK Stack

ArgoCD

GitLab CI

Job description

T-Hub Polska in Warsaw is seeking an AIOps Engineer to design, deploy, and maintain vLLM inference services on OpenShift/Kubernetes running on bare-metal GPU infrastructure. You will manage NVIDIA GPU resources to maximize usage across models and tenants.

The role focuses on automation, observability, and security, covering model lifecycle management, HPA, and monitoring dashboards in Grafana, with teams across AI and Platform collaborating. Remote/hybrid work options are available.