AI Infrastructure Engineer

Are you interested in being part of a company that shapes the future of space and cyber technologies? To have a job where you can contribute to real-world missions with long-term impact? On behalf of ESA ESRIN, we are looking for two AI Infrastructure Engineers to play a key part in bringing AI and LLM technologies into production, working across GPU infrastructure, Linux, Kubernetes, LLM deployment, automation, security, monitoring and Infrastructure as Code. You’ll help build the robust technology foundation that enables enterprise-grade AI services and MLOps capabilities. This is an exciting opportunity for experienced infrastructure or cloud engineers who wants to take the next step into AI and LLM technologies while working on a technically challenging project within the ESA environment. You’ll have the opportunity to work with modern technologies, solve complex infrastructure challenges, and have a tangible impact on how AI services are delivered and operated at scale. Tasks and activities - Deploy, configure, and operate Azure and on-premises AI infrastructure. - Build and manage GPU-based platforms for LLM inference and AI workloads. - Administer Linux servers, Docker containers, and Kubernetes clusters. - Deploy and support Mistral and other LLMs, exposing them through secure APIs. - Implement and manage vector databases and AI search services. - Develop Infrastructure-as-Code and CI/CD pipelines using Azure DevOps. - Monitor platform performance, availability, security, and cost efficiency. - Troubleshoot infrastructure, networking, storage, and GPU-related issues. - Implement backup, disaster recovery, patching, and security controls. - Produce and maintain technical documentation Skills and experience - Strong experience with Microsoft Azure infrastructure and networking. - Hands-on experience with GPU servers, NVIDIA drivers, CUDA, and AI workloads. - Advanced Linux administration and troubleshooting skills. - Experience with Docker and Kubernetes in production environments. - Experience deploying and serving LLMs using frameworks such as vLLM, Hugging Face TGI, Ollama, or equivalent. - Experience with vector databases and AI search technologies. - Knowledge of Infrastructure-as-Code tools such as Terraform, Bicep, or Ansible. - Experience with Azure DevOps and CI/CD automation. - Strong understanding of security best practices, identity management, secrets management, and infrastructure hardening. - Experience with monitoring, logging, backup, and disaster recovery solutions. The following skills and experience would be highly desirable: - Experience with Azure Kubernetes Service (AKS). - Experience operating on-premises AI platforms and private LLM deployments. - Familiarity with Mistral model management and optimisation. - Microsoft Certified: Azure Administrator Associate (AZ-104). - Microsoft Certified: Machine Learning Operations Engineer Associate (AI-300) Why should you apply? - You will have the opportunity to work within leading space organisations across Europe. - We encourage everyone to think outside the box and to push the boundaries of traditional knowledge. This role is an opportunity to join a forward-thinking company and allows for a deeper understanding of the industry. - To be part of a company that values integrity, inspiration, care and collaboration. - Benefits include: competitive remuneration packages; unique career opportunities, including working in other countries; access to training and development programmes; flexible relocation support.