Platform Engineer MOTS Infrastructure

Futures Works; Leusden; On-site; EUR 70,000 - 120,000; Full time

Benefits offered by this job

Ownership of infrastructure for AI平台

Hands-on role with NVIDIA GPUs and K8s

Competitive salary

EU Sovereign Cloud project

Job summary

Futures Works in the Netherlands is seeking a Platform / MLOps Engineer to build and operate the AI platform behind customer deployments in the EU Sovereign Cloud. You will integrate NVIDIA GPU capacity, Kubernetes, and model infrastructure to deliver secure, scalable workloads for regulated data.

You will deploy models, automate releases, implement IaC with Terraform/OpenTofu, and improve CI/CD and GitOps processes.

Qualifications

• Proven experience building and operating MLOps platforms.
• Strong knowledge of production Kubernetes and GPU workloads.
• Experience with AI/LLM deployments and model serving.

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 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 environments.
• Build and improve CI/CD and GitOps processes for platform components and model deployments.
• Implement 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 stability improvements.
• Collaborate with AI and software teams to transition experiments into production services.
• Document technical decisions and configurations clearly.

Skills

Kubernetes

NVIDIA GPUs

Python

Go

Bash

CI/CD & GitOps

Terraform/OpenTofu

Helm

Argo CD

Flux

NVIDIA Container Toolkit

Model deployment

Tools

Terraform

OpenTofu

Helm

Argo CD

Flux

DCGM

NVIDIA GPU Operator

Job description

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 organization's 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 client's 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 production—optimizing 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.