AI Platform Engineer - Secure GPU Inference & Scale

Leonardo; West of England; Hybrid; GBP 70,000 - 110,000; Full time

Benefits offered by this job

Time to Recharge

Pension up to 15%

Mental health support

Bonus scheme

Free online courses

Referral bonus

Flexible benefits

Hybrid working

Job summary

Leonardo is seeking AI Platform Engineers to shape, build, and operate the infrastructure that underpins its AI platform. You’ll enable secure, reliable access to AI models and inference services for engineering teams.

The role focuses on owning the platform layer above GPU infrastructure, deploying scalable inference services, and establishing engineering standards for secure enterprise operations, including air-gap or restricted networks. Hybrid UK-based role with global collaboration.

Qualifications

• Experience operating shared or business-critical platforms.
• Familiarity with large language models and the practical considerations of running them.
• Experience troubleshooting distributed systems and performance issues.
• Familiarity with infrastructure as code and CI/CD.
• Effective communication and stakeholder engagement.
• Curiosity and a drive for continuous improvement.

Responsibilities

• Take ownership of the platform layer above our managed GPU infrastructure, including model serving, inference runtimes, AI gateways and supporting services.
• Deploy and operate scalable inference services using containers, Kubernetes, and AI gateway platforms, improving observability and performance.

Skills

Linux administration

Containers

Kubernetes

AI inference platforms

API management

Python scripting

Monitoring and SRE

Security and access control

Tools

Docker

Kubernetes

vLLM

LiteLLM

SGLang

Bifrost

Job description

Leonardo is seeking AI Platform Engineers to shape, build, and operate the infrastructure that underpins its AI platform. You’ll enable secure, reliable access to AI models and inference services for engineering teams.

The role focuses on owning the platform layer above GPU infrastructure, deploying scalable inference services, and establishing engineering standards for secure enterprise operations, including air-gap or restricted networks. Hybrid UK-based role with global collaboration.