Tema

Språk

Global EN
Sverige ENSV
Indien EN

GPU HW Research Engineer (San Diego/Boxborough)

Teknik, data och digitalt · Mjukvaru- och webbutveckling · Mjukvaruutveckling · Artificiell intelligens · Maskininlärning

I korthet

Qualcomm's GPU Research Team is looking for innovative GPU architects to advance AI, ML, and GPGPU computing. You will design next-generation GPU architectures for diverse platforms, including mobile, WoS, and data center GPUs, collaborating with software and hardware teams on cutting-edge solutions and open-source projects.

Ansvarsområden

  • Collaborate with GPU architects to design new hardware features and enhance existing GPU architectures for GPGPU, ML, and AI workloads.
  • Develop architectural solutions for mobile, WoS, and data center GPUs.
  • Work closely with software teams, hardware design teams, standardization bodies, and partners.
  • Participate in open-source GPGPU/ML/AI projects.
  • Influence GPU capabilities for large language models (LLMs) and large vision models (LVMs).

Krav

  • Strong understanding of GPU architectures, programming models, and application domains.
  • Proficiency with APIs like OpenCL, CUDA, Vulkan, or Direct3D 12.
  • Experience with hardware design flow and basic knowledge of Verilog or VHDL.
  • Exposure to hardware simulation/emulation tools and waveform analysis.
  • Basic understanding of GPU memory and cache design hierarchy.
  • Solid programming skills in C/C++.
  • Bachelor's degree in Computer Engineering, Computer Science, Electrical Engineering, or related field and 4+ years of relevant work experience.
  • OR Master's degree in Computer Engineering, Computer Science, Electrical Engineering, or related field and 3+ years of relevant work experience.
  • OR PhD in Computer Engineering, Computer Science, Electrical Engineering, or related field and 2+ years of relevant work experience.

Önskade kvalifikationer

  • Familiarity with Python is a strong plus.
  • Hands-on experience in development, debugging, and optimization of CUDA and OpenCL kernels, as well as GPU compute shaders.
  • Deep understanding of quantization techniques and data types for large language models (LLMs) and large vision models (LVMs).
  • Experience designing GPU hardware features for ML/AI acceleration.
  • Experience with open-source projects such as llama.cpp, vLLM, or similar frameworks is a big plus.

Förmåner

  • 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.

Färdigheter

GPU architecturesprogramming modelsOpenCLCUDAVulkanDirect3D 12hardware designVerilogVHDLhardware simulationhardware emulationwaveform analysisGPU memory designcache designC/C++PythonCUDA kernelsOpenCL kernelsGPU compute shadersquantization techniquesdata typesllama.cppvLLM
#GPU#AI#ML#GPGPU#hardware#architecture#research#Qualcomm
Qualcomm Logo

Om Qualcomm

Enabling a world where everyone and everything can be intelligently connected.

Enabling a world where everyone and everything can be intelligently connected.\n\n

Qualcomm Logo

Företag

Qualcomm

Publicerade jobb

för 2 dagar sedan

Anställningstyp

Heltid

Arbetsform

På plats

Lön

169 500–254 300 US$ / år

Erfarenhetsnivå

Mellannivå

Platser

Boxborough, United States of America

San Diego, United States of America

Kvalifikation

Grundnivå, Masterexamen, Doktorand

Sökande

Ansök tidigt