Description
Qualcomm India Private Limited is hiring a GPU AI Performance Engineer to design, optimize, and accelerate AI workloads on GPU-based platforms. The role covers GPU architecture analysis, AI-stack optimization from model graphs and inference runtimes through GPU kernels and compiler IR, workload characterization across GPU generations, and data-driven architectural trade-off studies. Preferred qualifications include CPU/GPU architecture knowledge, Python, C++, and ML frameworks, while experience with LLM inference engines, GPU compiler pipelines, quantization, MoE architectures, GPU driver and compiler development, and OpenCL or CUDA is advantageous. Applicants need a bachelor's, master's, or PhD in a relevant field plus 6, 5, or 4 years of Systems Engineering or related experience, respectively.
