Compensation

Not specified

Currency: Not specified

City

Not specified

Country

Not specified

The GPU Performance Engineer – AI Workload Focus will optimize AI GPU workloads on Qualcomm architectures, focusing on maximizing throughput and efficiency. You will analyze kernel performance, identify bottlenecks, and implement CUDA/C++ optimizations, memory tuning, and parallelization strategies. The role involves benchmarking AI inference/training workloads, profiling using performance tools, and collaborating with AI software and hardware teams to drive scalable, power-efficient solutions. You'll contribute to driver/software stacks and work on end-to-end performance optimization from low-level routines to higher-level AI frameworks.