Computer Vision System Engineer

Qualcomm•San Diego, CA

2d•$122,500 - $213,200

About The Position

Qualcomm's computer vision system design Group is seeking candidates for its Mobile Computer Vision and AI Systems Architecture Team. The team develops next-generation mobile computer vision and deep learning solutions for imaging, perception, scene understanding, segmentation, tracking, computational photography, and AI-powered experiences. We are seeking candidates with strong expertise in hardware-aware algorithm design, deep learning engine architecture, system architecture, HW/SW co-design, and accelerator development for mobile computer vision and AI workloads. The ideal candidate will possess deep knowledge of computer vision and neural network algorithms and practical experience translating them into power-efficient, real-time implementations on heterogeneous mobile platforms consisting of CPUs, GPUs, DSPs, NPUs, and dedicated AI accelerators. The candidate is expected to drive architecture definition for next-generation deep learning engines and computer vision accelerators, including compute, memory, dataflow, scheduling, quantization, and HW/SW partitioning strategies that maximize performance-per-watt.

Requirements

Bachelor's degree in Computer or Electrical Engineering, Computer Science, or related field and 2+ years of Software Engineering, Hardware Engineering, Systems Engineering, or related work experience.
Master's degree in Computer or Electrical Engineering, Computer Science, or related field and 1+ year of Software Engineering, Hardware Engineering, Systems Engineering, or related work experience.
PhD in Computer or Electrical Engineering, Computer Science, or related field.
Strong understanding of mobile computer vision applications, including: Object Detection and Tracking, Segmentation, Scene Understanding, Image Enhancement and Computational Photography, Motion Estimation and Neural Network-Based Vision Systems
Expertise in system architecture and HW/SW partitioning for computer vision and AI workloads.
Strong understanding of deep learning accelerator architectures, including Tensor processing, optimization, compute and neural network bottlenecks
Experience defining real-time hardware architectures for computer vision and deep learning workloads.
Experience evaluating throughput, latency, power, memory bandwidth, and silicon area trade-offs.
Strong programming skills in C/C++ and Python with hands-on experience in algorithm prototyping and performance analysis.

Nice To Haves

Multiple years of experience developing mobile computer vision and AI systems.
Deep knowledge of modern neural network architectures, including CNNs, Transformers, Vision Transformers (ViTs), multi-modal perception systems, and hardware-aware model optimization techniques.
Experience architecting and optimizing deep learning engines (DLEs) or AI accelerators for computer vision workloads.

Responsibilities

Study state-of-the-art computer vision and deep learning models and define efficient mappings onto mobile AI accelerators and heterogeneous compute platforms.
Drive architecture development for hardware-aware deep learning engines, including support for emerging neural network operators, dataflows, tensor processing pipelines, quantization techniques, and memory hierarchies.
Analyze neural network workloads and identify architectural enhancements required to improve performance, power efficiency, memory bandwidth utilization, and silicon area.
Define HW/SW partitioning strategies across CPUs, GPUs, DSPs, NPUs, and dedicated accelerators.
Develop workload characterization methodologies and performance models for computer vision and AI applications.
Collaborate with hardware architects and designers to define next-generation AI engine features and capabilities based on evolving computer vision workloads.
Drive top-down architecture exploration from algorithm requirements through hardware implementation, including performance, power, thermal, and area projections.