This role pays less than
72%
of similar roles. Most pay
$188,800–$250,000
— the shaded band above.
At the midpoint, this role pays about
$190k
versus about
$219k
for comparable roles.
Based on 240 similar postings.
Employer
About Arm Holdings
Arm Holdings plc is a leading British semiconductor and software design firm, established in 1990 and recognized for developing energy-efficient processor architectures that power nearly all smartphones and a vast range of IoT and computing devices.
Arm Holdings currently has
105 open roles
on FindRole.
Listed pay typically runs
$209,100–$282,900
across 105 roles with salary data.
As a Senior GPU Architect within the Central Technology team, you will join a multifaceted Graphics Hardware Architecture group to shape the direction of Mali graphics products. You will collaborate with leading architects to build prototype architectural improvements, conduct technology research, and perform experimental investigations to deliver advanced future GPU IPs. Your daily work involves analyzing performance for gaming and GPGPU workloads while engaging with product groups to validate innovative ideas. The role requires expertise in the graphics pipeline, GPU architectures, and the trade-offs between GPU and CPU designs. You will utilize C and C++ to navigate large codebases and debug complex problems. Preferred skills include experience with OpenGL, Vulkan, DX, OpenCL, or CUDA, as well as performance modeling, timing-accurate simulators, hardware/software codesign, and system-level knowledge of how accelerators communicate with host CPUs.
Develop prototype architectural improvements for Mali Graphics products.
Conduct technology research and experimental investigations to inform future GPU designs.
Analyze the performance of various gaming and GPGPU workloads.
Identify system bottlenecks through detailed performance analysis of workloads.
Perform hardware/software codesign, specifically focusing on GPU drivers and interfaces.
Develop timing-accurate simulators for architectural modeling.
Propose innovative architecture ideas and submit patents for future IP generations.
What we're looking for
A Bachelor's degree with 6+ years of experience (including 2 years in GPUs), an MS with 4+ years of experience (including 2 years in GPUs), or a PhD with 2+ years of GPU experience.
Knowledge of the graphics pipeline and GPU architectures, including fixed function units for graphics processing.
A clear understanding of the trade-offs between GPU and CPU architectures.
Strong programming skills in C and C++ with an ability to work with large codebases and debug complex problems.
A solid academic background in computer architecture and a history of creative, analytical thinking.
Knowledge of graphics and compute APIs such as OpenGL, Vulkan, DX, OpenCL, or CUDA (preferred).
Experience in performance modeling, architecture, developing timing-accurate simulators, or hardware/software codesign (preferred).
System-level knowledge of accelerator communication and data transfer with the host CPU (preferred).
GPU Architecture
C
C++
Python
CUDA
OpenCL
Triton
Hip
TensorFlow
PyTorch
LLVM
MLIR
System C
RTL
HPC
Machine Learning
Kernel Prototyping
Performance Modeling