AI Infrastructure Engineer
- Department
- Engineering
- Employment Type
- Full-time
- Location
- UK / Remote
Viewrich is building practical AI and cloud infrastructure solutions for modern businesses.
We're looking for an AI Infrastructure Engineer to help us design, deploy and improve the infrastructure required to run AI workloads reliably and efficiently.
This role sits at the intersection of cloud infrastructure and AI engineering. You'll work with GPU compute, containers, cloud platforms and model-serving environments, helping turn infrastructure into reliable AI products.
What you'll work on
- Design and deploy infrastructure for AI and GPU workloads
- Build and maintain environments for LLM and machine learning workloads
- Deploy and operate AI model-serving environments
- Work with Docker, Kubernetes and cloud infrastructure
- Automate infrastructure provisioning and deployment
- Improve the reliability, performance and cost efficiency of AI workloads
- Help design scalable infrastructure for AI applications
- Work with networking, storage, security and observability components
- Troubleshoot infrastructure and workload performance issues
- Collaborate with engineers working on private AI and AI automation
What we're looking for
- Strong software engineering or infrastructure engineering fundamentals
- Experience with Python or another modern programming language
- Good understanding of Linux
- Experience with Docker and containerised workloads
- Familiarity with cloud infrastructure
- Understanding of networking and distributed systems
- Experience deploying or operating AI/ML workloads
- Strong problem-solving and debugging skills
- Ability to work independently and take ownership of technical problems
Nice to have
Experience with one or more of the following would be valuable:
- GPU infrastructure
- NVIDIA CUDA
- Kubernetes
- Terraform
- Kubernetes GPU workloads
- vLLM, Triton or other model-serving technologies
- LLM inference optimisation
- AWS, Azure or Alibaba Cloud
- Linux performance tuning
- Infrastructure monitoring and observability
What you'll help build
Your work may contribute to:
- AI Infrastructure — Infrastructure for GPU-accelerated AI workloads and modern AI applications.
- Model Serving — Reliable environments for deploying and serving AI models.
- Cloud Platforms — Infrastructure across public and private cloud environments.
- AI Operations — Automation and tooling that makes AI workloads easier to deploy, operate and scale.
Why Viewrich?
You'll work on practical AI infrastructure rather than isolated experiments.
The role gives you exposure to both sides of the stack — the infrastructure that runs AI and the products that use it.
As Viewrich grows, you'll have the opportunity to influence architecture, tooling and engineering practices from an early stage.
Interested?
If you're interested in building the infrastructure behind practical AI products, we'd like to hear from you.
Talk to Us