CPU/DSP Functional Modeling and Performance Engineer

Qualcomm•Austin, TX

77d

About The Position

Qualcomm is seeking a low-level embedded engineer with a strong foundation in software and processor architecture to help shape architectural features and deliver measurable performance enhancements on Qualcomm's Neural Processing Unit (NPU). This role will work across the instruction set architecture, operating system, and processor architecture, partnering tightly with hardware and software teams to turn ML workload insights into architecture and software optimizations. The ideal candidate will be proficient in processor architecture, C/C++ and assembly, embedded operating systems, and performance profiling tools. Experience with AI workloads and large language models (LLMs) is a plus but not required.

Requirements

Proficiency in debugging, performance analysis and profiling.
Strong background in operating systems, computer architecture, and micro-architecture (pipelines, caches, memory hierarchy, coherence).
Experience with multi-threaded and multi-processor systems.
Strong programming skills in C/C++, Python, or similar.
Excellent problemâsolving skills, attention to detail, and clear written/verbal communication.
Ability to collaborate across hardware/software domains.
Bachelor's degree in Electrical Engineering, Computer Science, Computer Engineering, or related field and 2+ years of relevant experience, OR
Master's degree in a related field and 1+ years of relevant experience, OR
PhD in a related field.
Bachelor's degree in Electrical Engineering, Computer Science, Computer Engineering, or related field and 2+ years of Software Engineering, Electrical Engineering, Systems Engineering, or related work experience.
Master's degree in Electrical Engineering, Computer Science, Computer Engineering, or related field and 1+ year of Software Engineering, Electrical Engineering, Systems Engineering, or related work experience.
PhD in Electrical Engineering, Computer Science, Computer Engineering, or related field.
2+ years of experience with high-performance microprocessor design.

Nice To Haves

Hands-on experience with debugging (gdb, lldb, winDbg or similar) and performance profiling tools (perf, VTune, Nsight or similar).
Familiarity with SIMD and SPMD execution models.
Understanding of hardware-software co-design principles.
Familiarity with linear algebra, and precision aware arithmetic is a plus.
Understanding of how ML architectures map to the hardware is a plus.
Knowledge of ML frameworks and libraries (ggml/llama.cpp or similar) is a plus.

Responsibilities

Model, benchmark, and analyze performance of multi-threaded and multi-processor software.
Identify and resolve performance bottlenecks across software, architecture, and micro-architecture layers.
Analyze ML KPIs to guide optimization efforts.
Collaborate with cross functional teams (architecture, compiler/runtime, kernel/RTOS, drivers, ML frameworks) to land optimizations in production.
Author clear design documents, performance studies, and best software practices.
Stay current with advancements in computer architecture, micro-architecture, and AI model design.

Benefits

We also offer a competitive annual discretionary bonus program and opportunity for annual RSU grants (employees on sales-incentive plans are not eligible for our annual bonus). In addition, our highly competitive benefits package is designed to support your success at work, at home, and at play.

Stand Out From the Crowd

Upload your resume and get instant feedback on how well it matches this job.

Upload and Match Resume