Senior DevOps Engineer - Kubernetes, Automation & AI Platform in Bern

Tasks
Design and further develop infrastructure completely as code - declarative, versioned and reproducible with Terraform, Ansible and Helm
Operate, scale and harden OpenShift/Kubernetes platforms for productive, highly available workloads
Automate CI/CD pipelines for build, test, security checks, deployment and rollback and implement GitOps principles
Develop automation and tooling solutions in Python, Bash or a comparable language such as Go or PHP
Operate and further develop the central LLM gateway based on LiteLLM, including routing, fallbacks, tenants, quotas, caching and failover
Make costs, usage, quality and security of AI workloads transparent and measurable
Develop, containerize, integrate and stably operate AI agents and AI services in production
Design monitoring, logging and tracing with Grafana, Prometheus, Splunk or Instana and perform sustainable root cause analyses
Implement exciting and demanding large-scale customer projects - from requirements to stable productive operation
Work closely with software development, IT operations, security and architecture as well as document systems, deployments and operational processes traceably

Requirements
Degree in computer science or a comparable education with corresponding practical experience
At least five years of experience in ICT projects, of which a substantial part is in DevOps, Platform Engineering or SRE
Sound practice with OpenShift or Kubernetes in productive operation as well as with Docker
Very good knowledge in CI/CD, automation and deployment processes with Jenkins, GitLab CI or GitHub Actions, Git and Maven
Solid experience with Terraform and Ansible as well as good programming experience for automation and tooling, preferably Python; other languages such as Go or PHP are welcome
Confident handling of monitoring, logging and observability solutions
Practical experience with AI-supported tools in everyday DevOps and interest in operating AI workloads
Basic knowledge of message brokers such as Kafka or RabbitMQ as well as of APIs and API gateways
Experience with agile methods as well as Jira and Confluence
Very good German, at least C1, and good English
A clear plus: experience with LLM gateways, LiteLLM, AI agents, RAG, vector databases, Public Cloud, FinOps, OpenSearch/Elasticsearch, Service Mesh, Policy-as-Code or Supply-Chain-Security

Languages
Very good German, at least C1, and good English