Machine Learning Framework, Compiler & Performance Engineer

Job Title

Machine Learning Framework, Compiler & Performance Engineer

Role Summary

Work on Qualcomm’s ML Systems Team to develop and evolve ML/AI compilers and tooling that map ML workloads efficiently to Qualcomm hardware. Responsibilities include compiler algorithm design, framework integration (PyTorch), workload analysis, performance simulation and pre-silicon performance prediction.

Collaborate with cross-site, cross-functional teams to influence future hardware and software features based on workload trends and performance trade-offs.

Experience Level

Mid-level. Specific years of experience not stated.

Responsibilities

Primary responsibilities include developing compiler algorithms, analyzing ML workloads, and building performance models and simulations.

• Design and implement algorithms to compile ML workloads for high performance and low power on Qualcomm hardware.
• Integrate PyTorch framework efficiently with Qualcomm compiler flows.
• Analyze ML network trends and customer requirements to drive hardware and software feature direction.
• Explore performance, area, and power trade-offs for future hardware and software ML algorithms.
• Create performance-driven simulation components using C++ and Python for pre-silicon analysis.
• Run, debug, and analyze performance simulations to identify compute and memory bottlenecks and recommend enhancements.
• Work in cross-site and cross-functional teams to deliver production and exploratory compiler solutions.

Requirements

Must-have skills and attributes, followed by additional assets.

• Strong background in algorithm development and performance analysis (essential).
• Proven problem-solving, analytical and debugging skills; detail-oriented.
• Effective written and verbal communication skills.
• Ability to learn, think and adapt in a fast-changing environment and work collaboratively across sites.
• Nice-to-have: C++ and Python experience; familiarity with compiler design and model formats (PyTorch, ONNX).
• Nice-to-have: experience with software development practices (git, CI/CD), Docker, Jenkins, clang/MSVC.
• Nice-to-have: on-silicon debug skills, knowledge of computer architecture, digital circuits, event-driven transactional simulators, and algorithms/data structures.

Education Requirements

Bachelor's degree in Computer Science, Engineering, Information Systems, or a related field.

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.