Senior DevOps Engineer

• Deploy, operate, and evolve a microservices-based platform running in Kubernetes clusters across AWS, GCP, and on-premises Rancher
• Operate and support GPU-based ML inference services using Triton Inference Server and vLLM on RunPod, Scaleway, and Nebius
• Build and maintain Docker images for all microservices and ensure a stable service lifecycle
• Maintain and scale development and production Kubernetes clusters
• Participate in deployment debugging, incident investigation, and performance troubleshooting
• Develop, maintain, and evolve custom Helm charts for each service
• Design and operate CI/CD pipelines using GitHub and GitLab for on-premises customer deployments
• Ensure platform compliance with SOC 2 requirements and improve security and compliance processes
• Manage cluster access via NetBird VPN and implement role-based access control using group policies
• Deploy and manage infrastructure using Terraform and Ansible
• Develop and continuously improve observability systems using Grafana, Prometheus, and the ELK stack
• Continuously optimize infrastructure across IaC, IAM, observability, and CI/CD
• Work with Python, Kubernetes, Linux, Docker, GitHub CI/CD, PostgreSQL, ClickHouse, Kafka, Superset, Terraform, and Ansible

• Minimum 5 years of experience in a DevOps and/or Site Reliability Engineering role
• Strong hands-on experience with Linux system administration
• Extensive experience deploying, operating, and scaling Kubernetes in both cloud and bare-metal environments
• Deep expertise and practical experience with at least one major cloud provider, preferably Google Cloud Platform
• Experience with ML inference on GPU/CPU is a strong plus
• Proven experience implementing SRE practices and building observability stacks using Grafana, Prometheus, and Loki
• Strong adherence to GitOps, Infrastructure as Code (IaC), and CI/CD principles
• Advanced expertise in Terraform, Ansible, and Python
• Ability to work in high-uncertainty environments and rapidly learn new technologies and patterns
• Proactive mindset and ability to debug and understand the product beyond DevOps tasks
• Strategic thinking for selecting technologies and architectural approaches based on long-term goals

• Fully remote
• 21 vacation days + public holidays + 5 sick days
• Private English lessons via Preply
• Fast career progression
• Startup pace with enterprise stability — real clients, real revenue, no bureaucracy
• Cutting-edge tech stack
• High engineering bar and real ownership
• Opportunity to work on award-winning AI products
• Exposure to Speech Technologies, NLP, Generative AI, LLMs, diffusion models, and voice-first agentic architecture