Machine Learning Compiler / Firmware Engineer

$127,200 - $190,800/Yr

Qualcomm - Austin, TX

Full-time - Entry Level

Hybrid - Austin, TX

Computer and Electronic Product Manufacturing

About the position

As a Machine Learning Compiler / Firmware Engineer at Qualcomm, you will be integral to the development of the machine learning compiler and runtime firmware for Qualcomm's advanced Neural Signal Processor. This role involves collaboration with a distributed team to optimize performance and ensure seamless integration with hardware, focusing on cutting-edge AI technology.

Responsibilities

• Collaborate with software architects and machine learning researchers to design and implement efficient PyTorch-based solutions.
• Develop and maintain the machine learning compiler, ensuring compatibility with the ATEN operator set.
• Optimize code for performance, memory usage, and power efficiency.
• Debug and troubleshoot issues related to the runtime firmware.
• Contribute to the development of a modern C++ project which uses extensive template metaprogramming techniques.
• Work independently and in a self-directed manner, while also collaborating effectively with remote team members.

Requirements

• Master's degree with 3 or more years of experience, or a PhD in Computer Science, Electrical Engineering, or a related field.
• Strong proficiency in Python and experience with PyTorch.
• Solid understanding of the ATEN operator set.
• Proficiency in modern C++ (C++17 or later).
• Experience with machine learning frameworks and compiler development is a plus.
• Excellent problem-solving skills and ability to work in a fast-paced environment.
• Strong communication skills for collaborating with remote team members.

Nice-to-haves

• Experience with high-performance microprocessor design.

Benefits

• Competitive compensation and benefits package.
• Flexible hybrid work arrangements.