DevOps

We are looking for a DevOps Engineer to join our team and take ownership of our infrastructure.
You will work with a modern Kubernetes-based environment, design scalable and reliable systems, and drive the adoption of AI-powered tools and practices across our workflows.

Your Responsibilities

• Design, maintain, and evolve Kubernetes cluster infrastructure and supporting services;
• Architect and optimize infrastructure (Hetzner) with a focus on scalability, fault tolerance, and cost control
• Administer databases (PostgreSQL, MongoDB, Redis, ClickHouse): replication, backups, performance monitoring, migrations
• Develop and maintain CI/CD pipelines (GitLab CI); implement GitOps practices
• Proactive incident management, post-mortem analysis, preventive measures; mentor the team in troubleshooting
• Build and evolve monitoring and alerting systems (Grafana, Prometheus, InfluxDB); define SLIs/SLOs
• Provide technical support to staff; mentor junior/middle DevOps engineers
• Participate in on-call rotations to ensure infrastructure availability

AI Adoption & AI Infrastructure

• Deploy and administer AI Gateway (LiteLLM) for unified access to LLM providers (OpenAI, Anthropic, GCP Vertex AI, AWS Bedrock, etc.)
• Configure routing, fallbacks, rate limiting, cost tracking, and logging via LiteLLM Proxy
• Integrate AI tools into team workflows: AI code review, AI-assisted incident management, routine task automation
• Deploy and maintain infrastructure for LLM/ML models on Kubernetes (GPU scheduling, model serving)
• Monitor AI service performance and costs; optimize token usage and latency
• Research and adopt new AI/ML tools that improve DevOps efficiency

We are open to candidates bringing their own tools and best practices in the AI space — and integrating them into our infrastructure.

Required Skills — Administration & Configuration

• Operating System: Ubuntu (deep understanding of systemd, networking, security hardening)
• Databases: PostgreSQL, MongoDB, Redis, ClickHouse — replication, backups, monitoring, performance tuning
• Containerization: Docker (optimized images, multi-stage builds, security best practices)
• Orchestration: Kubernetes (Helm, RBAC, network policies, HPA/VPA, cluster upgrades, troubleshooting)
• CI/CD: GitLab CI/CD (advanced pipelines, environments, security scanning, GitOps)
• Monitoring: Grafana, Prometheus, InfluxDB; dashboards, alerts, SLI/SLO definition
• AI Infrastructure: LiteLLM, experience with LLM API Gateways, understanding of LLM providers and their APIs

Tooling Skills

• Linux: firewall (iptables/nftables), DNS, network diagnostics, filesystems, performance tuning
• Cloud Providers: Hetzner, AWS (EC2, S3, RDS, IAM, VPC, EKS)
• Cloudflare: DNS, WAF, CDN, Workers, Zero Trust
• Atlassian: JIRA, Confluence — documentation and process management
• Languages: Python, Bash (automation, scripting); basic understanding of PHP

Nice to Have

• Kafka, RabbitMQ — production experience
• Deep understanding of computer architecture, processors, filesystems
• Networking protocols (TCP/IP, HTTP/2, gRPC, TLS)
• Experience with GPU infrastructure for ML/AI workloads
• MLOps experience: model serving (vLLM, TGI, Triton), experiment tracking
• Experience with MCP (Model Context Protocol), AI agents, RAG architecture
• Service mesh (Istio, Linkerd)
• HashiCorp Vault, cert-manager

Additional Requirements

• English — Upper Intermediate+ (confident reading of logs, technical documentation, writing documentation, communication with English-speaking colleagues)
• Experience mentoring and conducting code/infrastructure reviews
• Ability to write post-mortems and technical documentation
• Proactive mindset: ability to identify problems before they occur