Qualcomm
Qualcomm2h ago
LinkedIn

AI Software Engineer – NPU/Hexagon ...

Bengaluru, Karnataka, India
Mid Level

Auto Apply to 50+ AI Matched AI Software Engineer – NPU/Hexagon ... Jobs

Use Auto Apply Agents to Bulk Apply jobs with ATS Optimised Resumes, find verified Insider Connections for jobs at Qualcomm

Full Job Description

General Summary

We are seeking an embedded software engineer to develop and optimize AI software for Qualcomm NPU (Neural Processing Unit) and Hexagon DSP processors. The role focuses on high-performance neural network kernels, runtime efficiency, new operator enablement, and close collaboration with architecture teams on next-generation AI platforms.

Key Responsibilities

  • Develop and optimize AI software components for Qualcomm NPU and Hexagon DSP processors.
  • Implement high-performance neural network kernels/operators focusing on latency reduction, power efficiency, memory optimization, and throughput maximization.
  • 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 activities.

Required Skills And Experience

We are looking for candidates with 2 to 10 years of experience in embedded software development, preferably within AI, DSP, NPU domains, or performance-critical systems. Key technical requirements include:

  • C/C++ Expertise: Strong programming skills and solid understanding of processor architecture, operating systems (Linux/RTOS), and multi-processor concepts.
  • AI & Neural Networks: Deep knowledge of deep learning architectures, neural network operators, runtime systems, graph execution frameworks, and operator implementation.
  • Optimization Techniques: Experience with kernel optimization, fixed-point computation, quantization (INT8/FP16), mathematical/numerical optimization for speedup.
  • Hardware Awareness: Knowledge of memory hierarchy, cache behavior, MMU/IOMMU mechanisms, bandwidth optimization, and software-hardware co-optimization strategies for AI accelerators.
  • Low-Level Skills: Exposure to SIMD (SSE/AVX), vector processing, assembly language programming, profiling tools (perf/VTune/benchmarks), debugging techniques, or low-level hardware-software optimization methods.

Educational Requirements

We accept applications from candidates with the following combinations of education and experience:

  1. Bachelor's degree in Computer Science, Electrical/Electronic Engineering (or related field) combined with 2+ years of relevant work experience; OR Master's degree + 1+ year.
  2. Bachelor's degree in Systems Engineering or related field plus 3+ years of relevant work experience; OR Master's degree + 2+ years.
  3. PhD in Computer Science, Electrical/Electronic Engineering (or related field) combined with 1+ year of relevant work experience.

Diversity & Inclusion

Qualcomm is an equal opportunity employer. We are committed to providing a accessible hiring process for individuals with disabilities. For accommodations during the application or interview process, please contact our accessibility team directly via email at disability-accomodations@qualcomm.com.

Confidentiality Statement

All employees are expected to abide by Qualcomm's policies and procedures, including strict requirements regarding the protection of confidential information and proprietary data as permitted under applicable laws.

Company

Qualcomm

Qualcomm

Qualcomm, inspired by two and a half centuries of American ingenuity, builds cutting-edge technologies that expand what's possible for everyone.About Our InnovationsPioneering advancements from wirele...

Bengaluru, Karnataka, India
Posted on LinkedIn