Performance Optimization Architect/Manager

Overview

Performance Optimization Architect/Manager on Qualcomm’s GPU performance and architecture team, focusing on system-level analysis and new optimizations for Adreno GPUs.

What you'll do

• Conduct system-level performance and bottleneck analysis for GPUs and System-on-Chips (SoCs).
• Use hardware models (performance models, RTL test benches, emulators, silicon) to identify performance bottlenecks.
• Formulate workloads and test suites for applications spanning graphics, machine learning, automotive, video, and computer vision.
• Partner with architecture and design teams on trade-offs across system performance, area, and power.
• Build performance infrastructure including models, testbench components, and analysis/visualization tools.
• Lead efforts to improve turnaround time and enable early performance analysis in the product development cycle.

What you'll need

• Bachelor’s (BE/BTech) or Master’s (MS/MTech) degree in a relevant field; PhD is a plus or equivalent experience.
• Minimum 12 years of experience in computer graphics (or related) with exposure to performance analysis and SoC/GPU architectures.
• Knowledge of Graphics APIs including OpenGL, Vulkan, DirectX, or Metal.
• Strong understanding of SoC architecture, graphics pipeline, memory subsystem architecture, and Network-on-Chip (NoC)/interconnect architecture.
• Expertise in C/C++ and scripting languages (Perl/Python).
• Experience with Verilog/SystemVerilog and SystemC/TLM is highly advantageous.

Details

• Location: Bangalore, India.