DevOps Engineer (AI)

TL;DR

DevOps Engineer (AI): Building and maintaining scalable platforms for serving LLM workloads in production with an accent on GPU-based infrastructure and high-performance reliability. Focus on optimizing model serving solutions and automating deployment pipelines within a Kubernetes environment.

Location: Amsterdam, North Holland (Onsite)

Company

International IT staffing organization providing recruitment and project resourcing services across various global markets.

What you will do

• Design, build, and maintain a scalable platform for serving LLM workloads in production.
• Deploy and manage containerized workloads on Kubernetes, including GPU-based infrastructure.
• Implement and optimize model serving solutions such as vLLM, Triton, and TGI.
• Set up monitoring and observability using Prometheus and Grafana.
• Build and improve CI/CD pipelines and automate infrastructure using Python and Infrastructure as Code.

Requirements

• Strong experience with Kubernetes in production and solid Linux systems knowledge.
• Hands-on experience with GPU infrastructure and LLM/ML model serving.
• Proficiency with CI/CD tools and Python scripting.
• Familiarity with infrastructure automation tools such as Terraform or Ansible.
• Proven ability to manage high-performance workloads at scale.

Nice to have

• Experience working in regulated environments.
• Knowledge of cost optimization strategies for high-performance workloads.