Our client is a fast-growing Dutch start-up that develops innovative AI solutions for healthcare. They develop proprietary AI models / LLMs for this, which run on their own in-house servers. To manage and optimize this (no-cloud) environment, they are looking for a Site Reliability Engineer.

This position does not offer work permit /visa sponsorship and is therefore only open to candidates with EU/EEA country citizenship, or otherwise not in need of sponsorship. Thanks for your understanding.

The role 

As a Site Reliability Engineer, you are responsible for setting up and managing the on-premise infrastructure with the latest hardware, including NVIDIA GPUs. You work together with a small team that develops the software and AI models internally and ensures that the systems are optimized for performance and security. This means:

• Managing on-premise servers 
• Configuring and maintaining the Kubernetes cluster according to a GitOps approach 
• Ensuring that all resources are available reliably and securely 
• Ensuring optimal stability, uptime and performance 

What do we need?

Key knowledge and experience:

• At least 3 years of relevant work experience
• Experience with Kubernetes and Docker
• Knowledge of on-premise Linux server management, networking and storage
• You prefer to work on solutions with positive societal impact
• You are looking for a close-knit and social team in a start-up/scale-up environment
• You are pragmatic, hands-on and do not get stuck in over-analyzing problems
• You can work independently and like to solve things yourself, but are also not afraid to ask your colleagues for help
• Fluent in English and not afraid to work in a company with mainly Dutch colleagues
• You will not need work permit/visa sponsorship and you preferably live in The Netherlands or will move here on short notice (not dependent on job offer).

Nice to have:

• Experience with monitoring tools (Prometheus, Grafana)
• Experience with managing GPU resources
• Experience with GitOps (FluxCD)

What can you expect?

• A good salary and travel allowance
• 31 vacation days
• Option to work from home up to 2 days a week
• Possibility to grow into a lead role when the company grows
• You will become part of a company that develops its own state-of-the-art AI models and has access to the latest hardware.
• The opportunity to make a meaningful contribution to improving healthcare
• Wine tastings on Friday afternoons and fun team outings