Head of GPU Cloud

Head of GPU Cloud

About the Company

Building software foundation for next-generation accelerated computing platform for large-scale AI infrastructure

Industry
Computer Software

Type
Privately Held

About the Role

The Company is in search of a Head of GPU Cloud to spearhead the engineering team dedicated to the development of a next-generation accelerated computing platform. The successful candidate will be instrumental in defining the architecture and operating model for large-scale AI inference services, with a direct impact on GPU utilization, platform economics, and customer experience. This role demands a leader with a strong technical background in software engineering, particularly in the areas of cloud platforms, distributed infrastructure, and HPC. The Head of GPU Cloud will be responsible for shaping the platform architecture, production inference, and engineering strategy, and must have a proven track record in leading engineering teams and making critical technical decisions. Key responsibilities for the Head of GPU Cloud include building and scaling the engineering organization, setting the architecture for efficient AI workload management, and leading the optimization of production model serving. The ideal candidate will have at least 12 years of software engineering experience, with a focus on large-scale model inference and a deep understanding of technologies such as vLLM, TensorRT LLM, and TGI. Advanced knowledge of Kubernetes, containerized infrastructure, and practical experience with GPU memory behavior and high-bandwidth networking is essential. The role also requires a leader with strong technical and leadership judgment, capable of balancing performance, reliability, security, and customer experience across multidisciplinary teams. Experience in GPU cloud, AI infrastructure, and a track record of improving accelerator utilization and compute economics are highly valued.

Functions

• Engineering