- Build and scale the infrastructure that powers real-time AI inference across GPU fleets, bare-metal servers, serverless and containerised production systems - Help evolve Runware’s platform toward more elastic, on-demand infrastructure that can scale quickly with customer traffic and model demand - Make Runware faster, more reliable and more resilient by improving the critical paths behind our request entrypoints, inference services, queues, storage, load balancers and networking layer - Automate the hard parts of infrastructure operations, from provisioning and configuration through to CI/CD, deployment safety, progressive rollouts and rapid rollback - Build the observability backbone for a high-performance AI platform, with the signals needed to spot issues early, understand capacity and fix problems before customers feel them - Play a leading role in production operations, incident response, debugging and post-incident improvements, helping us turn operational challenges into a stronger platform - Strengthen the security and compliance foundations of our infrastructure through patching, secrets management, access controls, hardening, auditability, documentation and repeatable operational processes

• Operate and improve multi-region GKE clusters hosting hundreds of microservices across multiple environments from development through production • Manage the Kubernetes platform layer: Istio service mesh, cert-manager, external-dns, RBAC, HPA/KEDA autoscaling, HashiCorp Vault secret injection, and Helm-based deployments • Develop and maintain Terraform modules across multiple IaC repositories covering GKE, networking (Shared VPC, Cloud NAT, Private Service Connect), Cloud SQL, Cloud Storage, Dataproc, Cloud Composer, Vault, and web hosting • Maintain and extend Azure DevOps CI/CD pipelines using shared Terraform templates with multi-environment deployment workflows • Support Confluent Kafka infrastructure including Connect workers with JDBC source connectors, consumer group health monitoring, and Kafka-lag-based autoscaling with KEDA • Manage Redis Enterprise clusters on Kubernetes with operator-managed lifecycle and replication • Operate the observability stack: Grafana Cloud (Alloy, Loki, Mimir, Tempo, Pyroscope via Private Service Connect), kube-prometheus-stack, Google Managed Prometheus, OpenTelemetry Operator/Collector, Beyla, and Kubecost • Harden cluster security posture: NetworkPolicies, Pod Security Standards, admission policy enforcement, CrowdStrike Falcon, Lacework, kube-bench, and cert-manager with Let’s Encrypt ACME • Support data infrastructure including Cloud SQL (PostgreSQL), Dataproc (Spark), Cloud Composer (Airflow), Matillion CDC pipelines, Snowflake, and BigQuery • Manage DNS across multiple providers (Azure DNS, Cloudflare, GCP Cloud DNS) via external-dns, and support Azure APIM and Cloudflare CDN/WAF • Partner directly with application development teams to troubleshoot deployment failures, tune resource limits and autoscaling, and resolve Kafka consumer lag and connectivity issues • Contribute to the Internal Developer Portal (Backstage) and internal CLI tooling that enables self-service for product engineers.

• Design, implement, and evolve GCP-based infrastructure using Infrastructure as Code with Terraform and Google Cloud deployment automation patterns. • Build and maintain scalable CI/CD pipelines using Cloud Build, GitHub Actions, Jenkins, or equivalent platforms for application, infrastructure, and platform workloads. • Administer and optimize GCP delivery workflows including Cloud Build triggers, Artifact Registry, source integrations, deployment approvals, and service account access patterns. • Partner with engineering teams to improve build, release, and deployment workflows across microservices and cloud-native applications. • Implement robust observability across systems using Google Cloud Operations Suite, Cloud Logging, Cloud Monitoring, and related telemetry tooling. • Strengthen platform security by integrating secrets management, policy enforcement, vulnerability scanning, and least-privilege access control. • Manage and optimize containerized environments using Kubernetes, Helm, and Google Kubernetes Engine (GKE). • Drive reliability engineering practices including incident response, root cause analysis, SLO thinking, and automated remediation where appropriate. • Standardize reusable templates, modules, and platform patterns that improve developer productivity and consistency. • Mentor engineers and provide technical leadership on GCP architecture, deployment automation, release governance, and DevSecOps practices.

• Design, implement, and evolve Azure-based infrastructure using Infrastructure as Code with Terraform, Bicep, or ARM templates. • Build and maintain scalable CI/CD pipelines using Azure DevOps Pipelines for application, infrastructure, and platform workloads. • Administer and optimize Azure DevOps services, including Azure Repos, Pipelines, Artifacts, Boards, and service connections. • Partner with engineering teams to improve build, release, and deployment workflows across microservices and cloud-native applications. • Implement robust observability across systems using Azure Monitor, Log Analytics, Application Insights, and related monitoring tooling. • Strengthen platform security by integrating secrets management, policy enforcement, vulnerability scanning, and least-privilege access controls. • Manage and optimize containerized environments using Kubernetes, Helm, and Azure Kubernetes Service (AKS). • Drive reliability engineering practice, including incident responses, root cause analysis, SLO thinking, and automated remediation, where appropriate. • Standardize reusable templates, modules, and platform patterns that improve developer productivity and consistency. • Mentor engineers and provide technical leadership on Azure architecture, deployment automation, release governance, and DevSecOps practices.