Conditions: 🌍 Remote (RF, Moscow time ±2) 💰 Full-time employment, long-term project 💰 Salary: 250-270K RUB/month Gross 📄 Employment: via Individual Entrepreneur agreement

🛠 Tech stack and tasks:

• Support and development of the AI platform infrastructure in Yandex Cloud
• Automation of service deployment (MCP-Gateway, RAG, LLM, Open WebUI) in DEV/TEST/PROD environments
• Network security and access control (Security Groups, VPN, Interconnect, Keycloak)
• Backup management, monitoring of GPU nodes (A100) and LLM load
• Support for model environments (Qwen-2.35B, LLM, RAG, Open WebUI)

✅ Key requirements: 🔹 Orchestration: Kubernetes (Helm/kubectl/Ingress/NodePools) 🔹 IaC: Terraform (modules, YC), Ansible 🔹 CI/CD: GitLab CI, ArgoCD 🔹 Monitoring: Prometheus, Grafana, Loki, Alertmanager 🔹 Containerization: Docker, Docker Compose 🔹 Cloud: Yandex Cloud (IAM, VPC, Managed DB, Object Storage, Endpoints) 🔹 Networks: basic VPN, CIDR, NAT, TCP/UDP 🔹 OS/Scripting: Linux, Bash 🔹 Security: Keycloak Would be a plus: 🔸 Experience with GPUs (A100), LLMs, RAG, ML models.

📩 Apply: @AllaDemHR with the subject DevOps