
AI Platform Engineer - All Levels
AI
Leonardo UK is recruiting AI Platform Engineers across all levels to build and operate the infrastructure and services underpinning their AI platform, providing secure access to AI models and inference services. The role involves managing model serving, inference runtimes, AI gateways, and supporting services using containers, Kubernetes, and vLLM. Candidates should have experience with shared platforms, large language models, distributed systems, and infrastructure as code.
What you'll do
- Take ownership of the platform layer above managed GPU infrastructure, including model serving, inference runtimes, AI gateways and supporting services
- Deploy and operate scalable inference services using containers, Kubernetes, vLLM and AI gateway platforms
- Improve observability and performance, and investigate complex technical issues across the platform
- Establish engineering standards for operating AI services within a secure enterprise environment, including cases where the target system has no route to the internet
What you need
Must-have
KubernetesDockervLLMSGLangLiteLLMBifrostLinuxPython
Soft skills
CommunicationStakeholder engagementAdaptabilityCuriosityContinuous improvement
AI Platform EngineerDefense and Space ManufacturingKubernetesvLLMAI InferenceHybridFull-timeSecurity ClearanceEdinburgh