AI Software Engineer – NPU/Hexagon DSP Kernel Optimization

Job Area:

Key Responsibilities

• Develop and optimize AI software components for Qualcomm NPU and Hexagon DSP processors.
• Implement high-performance neural network kernels/operators with focus on latency, power, memory, and throughput.
• Profile runtime bottlenecks and apply hardware-aware software optimizations.
• Partner with architecture and hardware teams to improve future NPU and DSP capabilities.
• Support customer issue resolution, performance tuning, and platform bring-up.

Required Skills and Experience

• 2 to 10 years of experience in embedded software development, preferably in AI, DSP, NPU, or performance-critical systems
• Strong C/C++ programming skills and solid understanding of processor architecture, operating systems, and multi-processor concepts.
• Understanding of deep learning architectures, neural network operators, runtime systems, graph execution, and operator implementation.
• Experience with kernel optimization, fixed-point computation, quantization, mathematical/numerical optimization.
• Knowledge of memory hierarchy, cache behavior, MMU/IOMMU, bandwidth optimization, and software-hardware co-optimization for AI accelerators.
• Exposure to SIMD, vector processing, assembly, profiling, benchmarking, debugging, or low-level optimization techniques.

Minimum Qualifications