GPU Research Engineer- AI (San Diego / Boxborough )
Core
Design next-generation GPU architectures to accelerate AI, ML, and GPGPU workloads for mobile, Windows on Snapdragon, and data center platforms.
Role type
Senior IC GPU Research Engineer (AI/Hardware)
Builds
GPU hardware features and architectural solutions for mobile, WoS, and data center GPUs
Domain
Semiconductor / GPU Architecture / AI
Deliverable
production ML models
Required skills
GPU architecture design, C/C++ programming, CUDA/OpenCL/Vulkan/Direct3D 12 APIs, GPGPU programming models
Preferred skills
CUDA/OpenCL kernel optimization, quantization techniques for LLMs/LVMs, open-source contributions (llama.cpp, vLLM)
Technologies
CUDA, OpenCL, Vulkan, Direct3D 12, C++, Python, llama.cpp, vLLM
Responsibilities
Design new hardware features and enhance existing GPU architectures for AI/ML/GPGPU; Develop architectural solutions for mobile, WoS, and data center GPUs; Collaborate with software, hardware design, and standardization teams; Participate in open-source GPGPU/ML/AI projects; Influence GPU capabilities for LLMs and LVMs
Seniority
Senior, hands-on IC