GPU Power Systems Engineer
QualcommJob Title
GPU Power Systems Engineer
Role Summary
Work on GPU power and performance optimization across architecture, microarchitecture, and implementation. Develop power models and verification tests, analyze workloads and profiles, and drive pre-silicon and post-silicon power correlation.
The role sits in the GPU ASICs engineering team and requires close collaboration with RTL designers, architects, verification, compiler and driver teams, and silicon implementation/post-silicon teams.
Experience Level
Mid-level. The posting requests 5+ years of experience in low-power ASIC optimization (typical mid-career range: 3–7 years).
Responsibilities
Primary responsibilities include power analysis, modeling, verification, and cross-team collaboration.
- Analyze GPU architecture/microarchitecture and workloads to identify power and performance optimization opportunities.
- Create and maintain GPU power models and estimations for projection and correlation.
- Perform workload analysis, profiling, and characterization to inform power optimization.
- Develop and maintain tests for pre-silicon and post-silicon power verification.
- Work cross-functionally with RTL designers, architects, verification, compiler, driver, and silicon teams to implement optimizations and validate results.
- Support power/performance correlation between models, simulation, and silicon measurements.
Requirements
Key technical requirements and preferred skills.
- Must-have: 5+ years of experience in low-power ASIC optimization and related power analysis/modeling.
- Must-have: Scripting experience (Python or Perl) for analysis and automation.
- Must-have: Experience with workload profiling and power verification (pre- and post-silicon).
- Must-have: Ability to collaborate effectively with RTL, architecture, verification, compiler, driver, and silicon teams.
- Nice-to-have: Experience with industry power tools such as PrimeTime PX and Power Artist.
- Nice-to-have: Experience with graphics APIs (Vulkan, DirectX, OpenGL), GPU driver or compiler development, and GPU architecture.
- Nice-to-have: Familiarity with C/C++, Assembly, and HDL (Verilog/SystemVerilog) and design verification practices.
Education Requirements
Degree requirement: Bachelor's degree in Computer Engineering, Computer Science, Electrical Engineering, or a related field is expected (or equivalent practical experience). Preferred: Master’s or PhD in those fields. The posting also lists acceptable alternative combinations of education and experience (e.g., Bachelor's + ~4 years, Master’s + ~3 years, PhD + ~2 years of relevant work experience).
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.
