GPU Performance Analysis Engineer

Qualcomm • San Diego, CA

4d

About The Position

Qualcomm is one of the largest fabless design companies in the world providing hardware, software and related services to nearly every mobile device maker and operator in the global wireless marketplace. The Qualcomm Graphics System Team is responsible for the development of end to end and system on chip (SOC) architectural solutions for next generation of graphics processing units (GPUs) and compute devices.
Responsibilities:
In this role, your work will have critical impact in influencing next generation GPUs to be more efficient and to maintain competitive edge in Qualcomm Graphics solutions.
You will be contributing to performance analysis at GPU level for Graphics and Raytracing workloads such as benchmark/games by exploiting different SW/HW/Architectural knobs to find opportunities to improve perf.
Be engaged and contribute to competitive perf/power analysis for popular benchmark/games and to identify or be able to explain the gaps with reasonable evidence which could lead to next generation architecture/HW/SW enhancement opportunities.
Develop tools for efficient, streamlined and scalable debug/validation tasks.
Support presilicon workload enablement efforts for the analyzed workloads and games
This role requires understanding of gpu bottlenecks. This also requires understanding how rendering for games work (their graphics pipelines) as well as to be able to write small rendering applications using the gpu using graphics APIs such as vulkan and hlsl/glsl/spirv. For this role you need to be able to analyze performance silicon measurements in Android.

Requirements

• Understanding of GPU architecture
• Rendering knowledge and the ability to write rendering applications with vulkan and other graphics APIs
• Strong knowledge of python and C++
• Performance analysis experience
• Sharp analytical skillset
• Fluency in usage of latest AI tools for coding/debugging to solve system level problem
• Minimum of Bachelor degree required
• Bachelor's degree in Computer Engineering, Computer Science, Electrical Engineering, or related field and 6+ years of Software Engineering, Hardware Engineering, Systems Engineering, or related work experience.
• Master's degree in Computer Engineering, Computer Science, Electrical Engineering, or related field and 5+ years of Software Engineering, Hardware Engineering, Systems Engineering, or related work experience.
• PhD in Computer Engineering, Computer Science, Electrical Engineering, or related field and 4+ years of Software Engineering, Hardware Engineering, Systems Engineering, or related work experience.

Nice To Haves

• Masters degree or PhD
• 3-7 years of relevant experience
• Android experience
• GFXR capture/playback for vulkan. Render doc capture and interpretation of the data.
• Experience in competitive performance for GPU centric use cases
• Post-si debugging experience

Responsibilities

• Contributing to performance analysis at GPU level for Graphics and Raytracing workloads such as benchmark/games by exploiting different SW/HW/Architectural knobs to find opportunities to improve perf.
• Engage and contribute to competitive perf/power analysis for popular benchmark/games and to identify or be able to explain the gaps with reasonable evidence which could lead to next generation architecture/HW/SW enhancement opportunities.
• Develop tools for efficient, streamlined and scalable debug/validation tasks.
• Support presilicon workload enablement efforts for the analyzed workloads and games

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Number of Employees: 5,001-10,000 employees