Sovereign AI Platform Engineer T Cloud Public (m/f/d)
HybridGranada, Andalusia, Spain
Job Summary
Design and run Kubernetes environments optimized for AI inference, retrieval, experimentation, and agent execution in secure or isolated settings. Deploy and operate open-source or open-weight model stacks, model gateways, vector databases, and supporting platform components. Build reproducible platform automation using Infrastructure as Code and GitOps approaches for stable, auditable delivery. Manage local registries, package mirrors, secrets, access controls, storage, networking, and observability in environments with limited or no public cloud dependency. Optimize GPU, compute, and storage usage for reliable AI workloads while maintaining security and data sovereignty requirements. This role centers on open-source or open-weight LLM stacks, air-gapped or isolated deployment models, and auditable AI operations suitable for sovereignty-sensitive programs. Candidates will work with inference stacks like vLLM and Ollama, alongside Kubernetes, Helm, Terraform, and ArgoCD.
Required Qualifications
- 5+ years in platform engineering, DevOps, SRE, or MLOps
- strong Kubernetes and Linux expertise
- Proven experience with AI infrastructure, model serving, private or on-prem deployments, and production operations for LLM-based workloads
- Strong hands-on skills in Python
- automation tooling such as Terraform, Ansible, Helm, and GitOps workflows
- Good understanding of networking, storage, access control, monitoring, and operational hardening in high-security environments
- Comfortable working in sovereignty-driven environments where auditability, isolation, and controlled data handling are mandatory
- Please send CV in English
Desired Qualifications
- Inference and local serving stacks such as vLLM, Ollama, llama.cpp, or OpenAI-compatible self-hosted endpoints
- Open-source or open-weight models appropriate for sovereign deployment, for example coding-capable and general-purpose families hosted internally through approved serving layers
- Platform tooling such as Kubernetes, Helm, Terraform, Ansible, ArgoCD, private registries, Qdrant or similar vector stores, and Open WebUI or comparable internal interfaces
- Developer-facing integration options such as VS Code-compatible extensions, Continue-style local model connectors, or editor integrations pointed at internal APIs instead of external SaaS endpoints
- Hardware awareness covering GPU-backed nodes, CPU-only fallback options, storage performance, network isolation, and on-prem or dedicated infrastructure patterns
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.