• Du analysierst Anforderungen und entwickelst sichere Cloud- und Kubernetes-Lösungen • Du konzipierst, implementierst und betreibst moderne DevSecOps- und Plattform-Architekturen • Du berätst zu Architektur-, Security- und Betriebsfragen mit Fokus auf Skalierbarkeit und Automatisierung • Du integrierst Security-Prozesse und -Tools in bestehende CI/CD- und Kubernetes-Umgebungen • Du automatisierst Security- und Plattformprozesse, z. B. mit Python und APIs • Du unterstützt bei der Umsetzung von Projekten sowie im laufenden Betrieb • Du arbeitest eng mit interdisziplinären Teams zusammen und entwickelst Plattformen kontinuierlich weiter

• Design, implement, and manage highly available infrastructure for our cloud-based platforms (AWS). • Work with our internal engineering teams to architect and support AI/ML infrastructure, specifically managing AWS Lambda infrastructure, and some legacy SageMaker environments for model training, hosting, and inference. • Create and automate robust deployment pipelines using CI/CD tools (GitLab / GitHub Actions) for both web applications and machine learning models. • Build, maintain, and scale containerized applications with Docker and ECS/Fargate. • Implement MLOps best practices to streamline the transition of models from development to production. • Ensure system scalability and reliability through proactive monitoring, logging, and automated alerting. • Collaborate with both Product Engineers and Data Scientists to optimize performance, security, and infrastructure costs. • Manage and evolve our Infrastructure as Code (IaC) footprint.

• Assist in building, maintaining, and improving CI/CD pipelines in GitLab, with exposure to SAP platforms. • Support the automation of deployment, monitoring, and remediation processes under the guidance of senior engineers. • Help document CI/CD pipelines, templates, and operational procedures. • Participate in implementing DevSecOps best practices, including basic security and compliance checks. • Collaborate with infrastructure, security, and application teams to support on-prem (VMware) and cloud environments (GCP / Kubernetes). • Monitor pipelines and systems, troubleshoot issues, and escalate when necessary. • Continuously learn DevOps tools, cloud technologies, and automation practices.

• Design, build, and operate production Kubernetes clusters on bare-metal infrastructure. • Implement and operate custom Kubernetes networking solutions. • Develop and maintain custom Kubernetes operators and controllers. • Deploy and optimize NVIDIA GPU operators and custom scheduling logic for GPU workloads. • Build deep integrations between Kubernetes and underlying infrastructure. • Design and implement automation using Terraform, Ansible, Helm, and custom operators. • Manage production bare-metal infrastructure across multiple regions ensuring high availability, fault tolerance, and graceful degradation. • Build comprehensive monitoring, logging, and alerting using Prometheus, Grafana, and ELK stack. • Identify and resolve performance bottlenecks across infrastructure domains.