Intern, AI Application Engineer

This internship role focuses on shaping next-generation SoC and subsystem architectures by deploying and operating LLM inference services on NVIDIA GPU servers. The intern will build automated benchmark harnesses, configure KV cache offloading to network-attached storage, and analyze system performance bottlenecks. The position involves collaborating with FPGA, SoC, and firmware engineers to validate data paths and present storage requirements for future SSD controllers.