AI/ML Infrastructure Engineer
GPU Cloud and Infrastructure GPU Infrastructure
£133,000–£231,000/year (£11,083–£19,250/month) — Negotiable
Team and product context
- Team
- GPU Cloud and Infrastructure
- Specialization
- GPU Infrastructure
- Product family
- AI infrastructure
GPU infrastructure, cloud operations, site reliability and DevOps for hosted workloads.
Explore our products and servicesJob Description
Build the platform layer behind training, inference, GPU scheduling, and model-serving capacity. The work covers Kubernetes operations, observability, deployment pipelines, and practical capacity planning for AI workloads.
Requirements
- Experience running Kubernetes, containers, and cloud infrastructure for production systems
- Practical knowledge of GPU orchestration, model-serving platforms, or ML workflow tools
- Strong debugging skills across networking, compute scheduling, storage, and CI/CD
- Comfort working with ML engineers on training pipelines and inference reliability
- Practical knowledge of GPU orchestration, model-serving platforms, or ML workflow tools
- Strong debugging skills across networking, compute scheduling, storage, and CI/CD
- Comfort working with ML engineers on training pipelines and inference reliability
Responsibilities
- Operate GPU-backed training and inference environments
- Improve model-serving capacity, deployment safety, and observability
- Build CI/CD workflows for ML services and infrastructure changes
- Partner with engineering teams on incidents, performance issues, and capacity forecasts
- Improve model-serving capacity, deployment safety, and observability
- Build CI/CD workflows for ML services and infrastructure changes
- Partner with engineering teams on incidents, performance issues, and capacity forecasts
Benefits
- Work on infrastructure that directly supports AI API and hosting customers
- Own practical reliability improvements across GPU and serving systems
- Collaborate closely with ML, backend, DevOps, and support teams
- Own practical reliability improvements across GPU and serving systems
- Collaborate closely with ML, backend, DevOps, and support teams
How we hire
The sequence and format can vary by role.
Application
Initial review
Relevant assessments
Interviews
Decision
Offer and onboarding
Privacy and application documents
Submit only the information and documents requested for this role. For information on personal-data handling, read our Privacy Policy.
Read the Privacy Policy