Remote job
DevOps Engineer
Job details
About this role
Role overview Build and maintain the infrastructure behind a growing software platform and its AI inference services. The role covers Kubernetes operations, delivery pipelines, observability, and the GPU compute used to serve models.
Responsibilities - Operate and scale Kubernetes clusters across multiple regions. - Build and maintain CI/CD pipelines for platform services. - Develop monitoring, alerting, and incident response tooling. - Improve how GPU capacity is allocated for model inference. - Apply security practices and support compliance requirements.
Requirements - At least three years of experience in DevOps or site reliability engineering. - Strong experience with Kubernetes and container orchestration. - Proficiency with infrastructure-as-code tools such as Terraform, Pulumi, or CDK. - Experience building CI/CD pipelines, for example with GitHub Actions or ArgoCD. - Familiarity with GPU infrastructure and machine learning serving platforms.
Nice to have Experience with AWS or GCP, Docker, Prometheus, ArgoCD, or GitHub Actions.