The Job

Principal GPU AI Kernel Development Engineer

Technology, Data & Digital · Software & Web Development · Software Engineering · Machine Learning

Join for updates

In short

Qualcomm is looking for a Principal GPU AI Kernel Development Engineer to develop high-performance kernels and runtimes for GPGPU operations, including Machine Learning and Image Processing. This role involves working with graphics software stacks on various operating systems and collaborating with hardware designers to optimize GPU drivers for standard APIs.

Responsibilities

  • Develop and optimize Adreno GPU drivers for APIs like OpenCL, OpenGL ES, Vulkan, and DirectX.
  • Accelerate Machine Learning operations for inference and training on the GPU.
  • Work on runtimes and frameworks supporting Machine Learning and other GPGPU operations.
  • Collaborate closely with hardware designers to understand and improve hardware/software interfaces.
  • Write samples and documentation.
  • Develop unit tests and work with partners, external developers, and OEMs.

Requirements

  • Bachelor's degree in Applied Mathematics, Computer Science, Computer Engineering, Electrical Engineering, Software Engineering, or related field and 8+ years of Software Engineering, Hardware Engineering, Systems Engineering, Electrical Engineering, Game Rendering, or related work experience; OR Master's degree and 7+ years of experience; OR PhD and 6+ years of experience.
  • 3+ years of work experience with one or more programming language suitable for graphics (e.g., C++, C).
  • 2+ years of relevant GPU experience.

Desired Qualifications

  • Knowledge of Machine Learning Theory.
  • Familiarity with a Deep Learning Framework such as Pytorch.
  • Knowledge of GPGPU application development including Mathematical Operations and Image Processing.
  • Device driver development, including GPU or CPU.
  • Programming experience with Graphics APIs such as OpenGL ES/Vulkan/DX11/DX12.
  • Exposure to Embedded systems and Real-time operating systems.
  • Experience working with ARM architecture.
  • Familiarity with Git or other SCM tools.
  • Master's Degree in a relevant field.
  • 10+ years' experience with software development skills (e.g. data structure and algorithm design, object oriented or other software design paradigm knowledge, software debugging and testing, etc.).
  • 10+ years' experience with C++ programming experience.
  • Optimizing algorithms for GPU hardware using OpenCL or CUDA.
  • Experience with different NN architectures such as CNNs, LLMs, LVMs, etc.
  • Background in mathematical operations (e.g. linear algebra, fast math libraries, etc.).

Benefits

  • Competitive annual discretionary bonus program.
  • Opportunity for annual RSU grants.
  • Highly competitive benefits package designed to support success at work, at home, and at play.
  • Details about US benefits available at a link.
#GPGPU#Machine Learning#Image Processing#GPU Drivers#Runtimes#Android#Linux#Windows#Inference#Training#Frameworks#Unit Tests#OEMs
Qualcomm Logo

Company

Qualcomm

Job Posted

1 month ago

Employment Type

Full Time

WorkMode

On Site

Experience Level

Senior

Locations

San Diego, United States of America

Qualification

Bachelor, Master, Doctoral

Applicants

Be an early applicant