Senior AI Infrastructure Engineer

Job summary

The Senior AI Infrastructure Engineer role is centered on developing and managing the infrastructure for AI models, ensuring efficiency and reliability at scale. Responsibilities include overseeing GPU clusters, enhancing inference performance, and facilitating distributed training, utilizing technologies such as Kubernetes and Triton Inference Server.

Qualifications

• A strong engineering foundation
• Production model deployment experience
• GPU cluster and orchestration experience
• Performance debugging skills
• Strong software and systems skills
• Operational ownership

Responsibilities

• Build and own model-serving infrastructure
• Manage GPU clusters and workload scheduling
• Improve inference performance
• Support distributed training and model iteration
• Make deployments observable and incidents traceable
• Own production reliability
• Make compute costs actionable
• Build a platform the model team can use independently

Skills

Relocation