DevOps Engineer for AI Inference Platform (Remote/Hybrid)

Devopsroles; United States; Hybrid; USD 120,000 - 180,000; Full time

Benefits offered by this job

Competitive compensation

Flexible hours

Hybrid/Remote options

Private medical insurance

Extra paid leave

Life-event support

Language courses

Modern offices with snacks

Job summary

AtGcore is seeking a talented DevOps Engineer to join our AI Inference Operations Team in the United States. You will design, deploy, and maintain infrastructure for scalable and secure AI inference workloads on-premises, collaborating with ML engineers to optimize performance at scale.

The role demands strong Kubernetes expertise, Linux networking skills, and hands-on IaC automation using Terraform/Ansible, with experience in Grafana/VictoriaMetrics for observability and GitOps workflows.

Qualifications

• Strong understanding of Kubernetes architecture and control plane components.
• Hands-on experience operating and troubleshooting production Kubernetes clusters.
• Strong Linux and networking troubleshooting skills (DNS, routing, TLS, firewalls, performance).
• Ability to develop automation and operational tooling using Python, Go, or Bash.
• Experience with IaC/configuration management tools (Terraform, Ansible).
• Experience with monitoring/observability tools (Grafana, VictoriaMetrics).
• Git-based workflows and CI/CD pipelines.

Responsibilities

• Design, deploy, and maintain infrastructure for AI inference workloads (on-prem).
• Build and manage monitoring/observability tools, dashboards, alerts, and runbooks.
• Collaborate with ML engineers to design system architecture and test performance at scale.

Skills

Kubernetes

Linux

Networking

Automation scripting

IaC (Terraform/Ansible)

Monitoring (Grafana/VictoriaMetrics)

Git CI/CD

Tools

Terraform

Ansible

Argo CD

Kubernetes Operators

Job description

AtGcore is seeking a talented DevOps Engineer to join our AI Inference Operations Team in the United States. You will design, deploy, and maintain infrastructure for scalable and secure AI inference workloads on-premises, collaborating with ML engineers to optimize performance at scale.

The role demands strong Kubernetes expertise, Linux networking skills, and hands-on IaC automation using Terraform/Ansible, with experience in Grafana/VictoriaMetrics for observability and GitOps workflows.