Platform Engineer MOTS Infrastructure

Platform / MLOps Engineer / EU Sovereign Cloud

About the Company

Our client is a pioneering European technology company building independent AI solutions for organizations that work with sensitive information and operate in highly regulated sectors. They help professionals put their organizations knowledge to work while retaining strict control over their data processes and expertise.
European ownership infrastructure and governance form the foundation of their approach. They combine open-source models with a proprietary platform working alongside domain experts to develop applications that fit specific professional needs. For example their tailored solutions for the notarial and legal sectors help teams search documents obtain answers grounded in proprietary information generate drafts and streamline workflows. These applications depend on a robust platform that handles sensitive customer data and heavy AI workloads securely and reliably.
The Role

As an MLOps Engineer / AI Platform Engineer you will build and operate the technical environment behind our clients AI applications and secure customer environments. You will bring together NVIDIA GPU capacity Kubernetes and AI model infrastructure to create a reliable secure and manageable platform.
The successful candidate will deploy models provision customer environments and automate releases. Your work will span the full stack of infrastructure: GPU resources networking storage model serving monitoring and access management. You will take full responsibility for how models run in productionoptimizing their performance under load ensuring observability and executing safe updates. By investigating bottlenecks and balancing performance against capacity and cost you will help AI and software engineers bring new AI applications into production with confidence.
Key Responsibilities

• Build operate and improve Kubernetes environments for AI workloads and customer applications.
  
• Make NVIDIA GPUs available to workloads and provide deep visibility into GPU utilization and capacity.
  
• Automate AI and LLM deployments encompassing configuration versioning and controlled updates.
  
• Configure and optimize model-serving environments for latency throughput and highly efficient GPU memory usage.
  
• Provision customer environments with strict isolation of workloads data network traffic and access.
  
• Develop Infrastructure as Code (IaC) and reusable configurations for consistent reproducible environments.
  
• Build and improve CI/CD and GitOps processes for platform components and model deployments.
  
• Implement comprehensive monitoring logging and alerting for infrastructure GPUs model endpoints and customer environments.
  
• Enhance platform availability backups recovery procedures and capacity planning.
  
• Investigate incidents resolve root causes and implement lasting stability improvements.
  
• Collaborate closely with AI and software engineering teams to transition experiments into stable production services.
  
• Document technical decisions configurations and operational procedures clearly.
  

Candidate Requirements

Our client is looking for a practical hands-on engineer who thrives on understanding complex systems and takes ownership of their reliability. You should be able to build and operate infrastructure while keeping the day-to-day needs of developers and end-users in mind.

• Proven experience as an MLOps Engineer AI Platform Engineer Infrastructure Engineer DevOps Engineer SRE or in a similar technical role.
  
• Strong knowledge of production Kubernetes including deployments scheduling networking storage and access control.
  
• Hands-on experience managing NVIDIA GPUs within Linux and containerized environments.
  
• Experience running or supporting AI and LLM workloads utilizing tools such as vLLM NVIDIA Triton TensorRT-LLM or similar technologies.
  
• Proficiency with Infrastructure as Code (e.g. Terraform OpenTofu) and deployment tooling (e.g. Helm).
  
• Solid understanding of CI/CD ideally including GitOps workflows using tools like Argo CD or Flux.
  
• Experience monitoring and troubleshooting complex distributed systems.
  
• Strong scripting or programming skills in languages such as Python Bash or Go.
  
• A foundational understanding of network security secrets management and data isolation between customer environments.
  
• A methodical independent approach to problem-solving and the ability to explain technical trade-offs clearly to stakeholders.
  

Bonus Points For:

• Experience with NVIDIA GPU Operator NVIDIA Container Toolkit and GPU monitoring with DCGM.
  
• Knowledge of GPU sharing MIG multi-GPU inference and GPU workload scheduling.
  
• Experience optimizing LLM inference through batching quantization or KV-cache management.
  
• Experience working with private cloud on-premises infrastructure or environments with restricted external connectivity.
  
• Familiarity with model registries artifact storage and reproducible model releases.
  
• Experience improving networking and storage performance specifically for large models and datasets.
  
• Prior experience in secure or regulated environments where changes and access must be demonstrably controlled.
  

What Our Client Offers

• Full ownership of the infrastructure powering cutting-edge AI applications and specialized customer environments.
  
• A highly technical hands-on role working directly with NVIDIA GPUs Kubernetes and modern AI/LLM ecosystems.
  
• The autonomy to shape architecture automation strategies and internal platform standards.
  
• Direct impactful collaboration with the engineers actively developing AI models and applications.
  
• A competitive salary and attractive employment conditions.
  
• The unique opportunity to help build sovereign independent European AI for professional use.
  

How to Apply

Please submit your CV along with a brief description of a platform or technical environment you played a key role in your application please highlight:

1. What ran on the platform and what were your specific responsibilities
   
2. A specific challenge you solved involving Kubernetes GPUs model deployments or reliability.
   
3. A technical trade-off you had to make and what you learned from the experience.