devops engineer.

You will join an innovative team at the forefront of AI deployment, offering high technical ownership and career evolution. In return, you will receive:

• A competitive compensation package commensurate with experience.
• Remote or Hybrid working schedule
• The opportunity to work on complex, high-impact LLM infrastructure projects across hybrid environments.
• A collaborative, tech-forward culture with access to the latest AI tools and hardware architectures.

As our DevOps / Cloud / Infrastructure Engineer, you will build and maintain the robust foundational systems that keep our AI-driven microservices running seamlessly. Your core responsibilities will include:

• Hybrid Orchestration: Design, deploy, and manage highly scalable Kubernetes clusters across both AWS (EKS) and self-hosted, bare-metal environments.
• Pipeline Automation: Build and manage automated CI/CD pipelines using GitHub Actions to deliver rapid, reliable deployments.
• Packaging & Configuration: Utilize Helm for managing complex, multi-environment Kubernetes deployments and application packages.
• Architecture & Scalability: Architect resilient, scalable microservices infrastructure tailored to meet the computational and operational demands of LLM applications.

To excel in this position, you should bring expert-level container orchestration skills along with a solid understanding of modern AI infrastructure needs. We are looking for:

• Kubernetes Expertise: Deep knowledge of container orchestration, cluster management, and scaling strategies for cloud-managed (EKS) and self-hosted environments.
• Cloud & Automation Stack: Strong hands-on experience with AWS, GitHub Actions, and Helm package management.
• LLM Fundamentals: A solid understanding of Large Language Models and their unique operational requirements.
• Architecture & Version Control: Excellent grasp of scalable microservices design and modern Git workflows.

While not mandatory, the following hands-on experience and skills will significantly support your application:

• Experience with hypervisors and virtualization technologies (e.g., KVM, VMware, Proxmox).
• Hands-on experience deploying LLM inference engines (e.g., vLLM, llama.cpp) and GPU orchestration in Kubernetes (NVIDIA device plugins, CUDA scheduling).
• Proficiency with Infrastructure as Code (IaC) tools such as Terraform or Ansible.
• Knowledge of advanced networking, service meshes (Istio, Linkerd), and secure cloud/on-prem connectivity.
• Hands-on development experience in Python or Go for custom tooling, automation, or Kubernetes operators.
• Familiarity with AI coding assistants (e.g., GitHub Copilot, Codex, Devin).

3+ years of experience as a Cloud/DevOps Engineer

Got any questions regarding this position? You can contact Konstantinos Adamopoulos at 6940080281, from Monday to Friday. Otherwise, feel free to contact me at kadamopoulos@randstad.gr.

We look forward to receiving your application, uploading your updated CV by clicking the 'apply now' option.

In case that your application advances to the next stage, you may be automatically invited to submit a video, answering a few interview questions.

Please note that for transparency and equity reasons, only those applications made online via our site will be assessed. After the screening of all the CVs received, we will only contact the candidates who meet the requirements of the job to arrange an interview. ​All applications are considered strictly confidential.