DevOps/Cloud/Infrastructure Engineer

Location: Remote / Hybrid (Must be currently based and residing in Greece) About Us KissMyButton, founded in 2004, is a team of dedicated software development professionals committed to helping clients unlock their full potential. With expertise spanning the entire software development lifecycle, the company delivers tailored, optimal solutions from ideation to execution. KissMyButton is driven by a vision of enabling entrepreneurial success by turning innovative ideas into impactful software. We are seeking an experienced DevOps/Cloud/Infrastructure Engineer to join our efforts in designing, developing, deploying and scaling our LLM-powered applications across both cloud and on-premise environments. In this role, you will bridge the gap between advanced microservices architecture and artificial intelligence, ensuring our platform runs seamlessly whether it is hosted on AWS or deployed on bare-metal servers. You will leverage deep Kubernetes expertise to build robust systems, streamline CI/CD pipelines, and bring cutting-edge LLM infrastructure to production anywhere. Required Skills (Must Have) Expert-level Kubernetes: Deep knowledge of container orchestration, cluster management, and scaling strategies for both cloud-managed (EKS) and self-hosted environments.Solution Architecture: Excellent understanding of designing, deploying, and maintaining scalable microservices architectures.LLM Fundamentals: Solid understanding of Large Language Models and their operational and computational requirements.Cloud Infrastructure: Strong hands-on experience with AWS and general cloud computing best practices.CI/CD & Automation: Proven ability to build and manage automated deployment pipelines, specifically using GitHub Actions.Package Management: Hands-on expertise with Helm for managing complex, multi-environment Kubernetes deployments.Version Control & Packaging: Strong proficiency in Git workflows and modern software packaging standards. Bonus Points (Nice to Have) Hypervisor & Virtualization: Experience with hypervisors (e.g., KVM, VMware, Proxmox) and managing virtualized on-premise infrastructure.LLM Inference Engines: Hands-on experience deploying and optimizing models using engines like vLLM, llama.cpp, or similar frameworks.GPU Orchestration: Familiarity with provisioning and managing GPU resources within Kubernetes (e.g., NVIDIA device plugins, CUDA scheduling).Infrastructure as Code (IaC): Experience with tools like Terraform or Ansible to automate provisioning across both cloud and on-prem environments.Advanced Networking: Deep understanding of hybrid networking concepts, routing, service meshes (like Istio or Linkerd), and secure cloud/on-prem connectivity.AI Coding Assistants: Familiarity with AI software engineers and developer tools (e.g., GitHub Copilot, Codex, Devin) to accelerate workflows.Python or Go Coding: Hands-on development experience with Python and/or Go for kubernetes operators, tooling, automation, or service development.