GPU HW Research Engineer
QualcommJob Title
GPU HW Research Engineer
Role Summary
Design and architect GPU hardware features to accelerate GPGPU, ML, and AI workloads across mobile, Windows-on-Snapdragon (WoS), and data-center platforms. Work within Qualcomm's GPU research team to propose, evaluate, and drive architectural solutions from concept through collaboration with software and hardware implementation teams.
Experience Level
Mid-level. Typical hire has several years of relevant industry experience (see Education Requirements for degree/experience combinations).
Responsibilities
Key duties include:
- Design new GPU hardware features and enhance existing GPU architectures for GPGPU, ML, and AI.
- Develop architectural solutions for mobile, WoS, and data-center GPU platforms.
- Collaborate with software teams, hardware design teams, standardization bodies, and partners to deliver solutions.
- Work with hardware simulation/emulation and validation flows to evaluate proposals.
- Contribute to open-source GPGPU/ML/AI initiatives and influence GPU capabilities for LLMs and large vision models.
Requirements
Must-have technical skills and experience:
- Strong understanding of GPU architectures, programming models, and application domains.
- Proficiency with GPU compute APIs (OpenCL, CUDA, Vulkan, or Direct3D 12).
- Experience with hardware design flows and basic HDL knowledge (Verilog or VHDL).
- Familiarity with hardware simulation/emulation tools and waveform analysis.
- Basic knowledge of GPU memory and cache hierarchies.
- Proficient programming skills in C/C++; Python is a strong plus.
Nice-to-have:
- Hands-on development, debugging, and optimization of CUDA/OpenCL kernels and GPU compute shaders.
- Deep understanding of quantization techniques and ML data types for LLMs and large vision models.
- Experience designing GPU hardware features specifically for ML/AI acceleration.
- Contributions to or familiarity with open-source ML/GPU projects (for example, llama.cpp, vLLM).
Education Requirements
Bachelor's in Computer Engineering, Computer Science, Electrical Engineering, or related field with 4+ years relevant experience; OR Master's in a related field with 3+ years; OR PhD in a related field with 2+ years. Related work experience in software, hardware, or systems engineering may be accepted in lieu of degree-specific experience as described above.
About the Company
Company: Qualcomm
Headquarters: San Diego, California, United States
Qualcomm is a global leader in semiconductor and telecommunications equipment, specializing in mobile technologies and innovations. Known for its Adreno GPUs, the company provides solutions enabling advancements in mobile gaming, AI, VR/AR, and autonomous driving. Qualcomm's cutting-edge technology and commitment to high-performance, power-efficient designs drive the evolution of mobile graphics and connectivity worldwide.
