AI Inference & MLOps SRE — Kubernetes & GPU

DCG; Polska; Hybrid; PLN 240,000 - 360,000; Full time

Benefits offered by this job

Private medical care

Co-financing for sports card

Training & learning opportunities

Constant support of dedicated consult

Job summary

DCG is seeking an experienced DevOps/SRE professional to support AI infrastructure projects. Design, deploy, and operate vLLM inference services on OpenShift/Kubernetes with bare-metal GPU hardware and manage NVIDIA GPUs and registries.

You will implement autoscaling, observability with Prometheus, Grafana, OpenTelemetry, and ELK; monitor performance and security; collaborate with AI/Platform teams to deliver scalable services. Strong Kubernetes/OpenShift, Python, Bash, and IaC skills required.

Qualifications

• 5+ years of experience in DevOps, SRE, Platform Engineering or Infrastructure Operations.
• At least 2 years hands-on experience supporting MLOps, AI Infrastructure, or LLM platforms.
• Strong experience with Kubernetes and OpenShift administration in production environments.
• Proven experience deploying and operating vLLM-based inference platforms in production.
• Deep knowledge of NVIDIA GPU technologies, CUDA drivers, NVIDIA Container Toolkit, and GPU troubleshooting.
• Hands-on with Prometheus, Grafana, OpenTelemetry, and ELK Stack.
• Strong Python and Bash scripting skills; Linux systems administration.

Responsibilities

• Design, deploy, and maintain vLLM inference services on OpenShift/Kubernetes with bare-metal GPU hardware.
• Manage NVIDIA GPU resources including partitioning and allocation for multi-model tenancy.
• Automate model lifecycle management including onboarding, versioning, deployment, hot-swapping, and rollback.
• Implement Horizontal Pod Autoscaling based on workload and GPU utilization.
• Build and maintain observability with metrics, logs, tracing, and dashboards in Grafana/Prometheus/OpenTelemetry/ELK.
• Instrument endpoints to expose token usage, latency, throughput, and errors.
• Develop usage tracking for API keys, users, teams, and departments for quota management.
• Create Grafana dashboards covering infrastructure health, GPU usage, and inference performance.
• Configure alerting with Prometheus and Alertmanager for failures and anomalies.
• Implement API Gateway for auth, rate limiting, and intelligent routing to inference services.
• Ensure secure operation via network segmentation and ingress/egress controls.
• Maintain audit logging for compliance and governance.
• Collaborate with AI Eng, Platform Eng, Security, and Infra teams on scalable, reliable services.
• Participate in troubleshooting, incident response, and platform improvements.

Skills

Kubernetes

OpenShift

vLLM

NVIDIA GPUs

Python

Bash

Linux

Prometheus

Grafana

OpenTelemetry

ELK Stack

IaC

GitLab CI

Jenkins

ArgoCD

Tools

OpenShift

Kubernetes

Hugging Face Enterprise

S3 (private registries)

NVIDIA Container Toolkit

Grafana

Prometheus

Alertmanager

APIs Gateway

Job description

DCG is seeking an experienced DevOps/SRE professional to support AI infrastructure projects. Design, deploy, and operate vLLM inference services on OpenShift/Kubernetes with bare-metal GPU hardware and manage NVIDIA GPUs and registries.

You will implement autoscaling, observability with Prometheus, Grafana, OpenTelemetry, and ELK; monitor performance and security; collaborate with AI/Platform teams to deliver scalable services. Strong Kubernetes/OpenShift, Python, Bash, and IaC skills required.