Head of GPU Cloud

Job Summary

Leading the engineering organization for a nationwide GPU cloud platform, the full-time Head of GPU Cloud will manage the architecture and execution of AI inference services, collaborating closely with cross-functional teams in a remote environment.

Key responsibilities

• Build and scale the engineering organization responsible for GPU cloud services, focusing on inference, orchestration, and platform reliability
• Set the architecture for efficient AI workload management, including routing, model lifecycle, and scheduling
• Establish engineering standards and team accountability while recruiting and developing senior technical talent

Required qualifications

• 12+ years of progressive software engineering experience with leadership roles in cloud platforms or distributed infrastructure
• 5+ years leading engineering teams focused on business-critical infrastructure or mission-critical technology products
• Demonstrated experience with large-scale model inference and optimization technologies such as vLLM and TensorRT LLM
• Advanced knowledge of Kubernetes and containerized infrastructure practices
• Practical knowledge of GPU infrastructure, including memory behavior and high bandwidth networking