Senior Developer Technology Engineer, Windows AI Platform

What you'll do

• Solve end-to-end AI GPU deployment challenges on the NVIDIA RTX platform for internal and external partners.
• Use profiling and debugging tools to identify and fix suboptimal runtime performance in GPU-accelerated applications.
• Develop sample code, conduct hands-on training, and host presentations regarding efficient AI deployment on ARM-based SoCs.
• Enhance Windows LLM and GenAI user experience by improving features and performance of open-source software like Llama.cpp and Ollama.
• Provide real-world workflow feedback to GPU driver and architecture teams to influence next-generation hardware features.
• Provide technical leadership and mentorship to junior engineers within the team.

What we're looking for

• Bachelor's or Master's degree in Computer Science, Engineering, or a related field.
• 8+ years of professional experience in local GPU deployment, profiling, and optimization.
• Strong proficiency in C/C++, Python, software design, and programming techniques.
• Experience with CUDA and NVIDIA's Nsight GPU profiling and debugging suite.
• Development experience on the Windows operating system.
• Experience working with open-source LLM and GenAI software.
• Preferred experience with NVIDIA APIs such as cuDNN, CUTLASS, and TensorRT.
• Expert knowledge in Vulkan or DX12 and familiarity with ARM architectures.