Staff ML Compiler Engineer, On‑Device AI

Qualcomm; Santa Clara (CA); On-site; USD 160,500 - 240,700; Full time

Job summary

Qualcomm is seeking an experienced compiler engineer to join the Qualcomm AI Hub Compiler team in Santa Clara, CA. You will design and maintain the end-to-end compilation pipeline while ensuring models compile correctly and efficiently across multiple backends.

The ideal candidate should have strong proficiency in Python and C++, as well as experience in ML infrastructure or compiler engineering. This position offers a competitive salary range from $160,500 to $240,700, along with bonuses and RSU grants.

Qualifications

• 4+ years of experience in hardware, software, or systems engineering.
• 3+ years of industry experience in ML infrastructure, compiler engineering, or AI framework development.
• Proficient in building automated CI/CD pipelines for model compilation and validation.

Responsibilities

• Design and maintain the end-to-end compilation pipeline for Qualcomm AI Hub.
• Contribute to ONNXRuntime QNN execution provider's optimizations.
• Own compilation and validation of models published on Qualcomm AI Hub.

Skills

Python

C++

ML infrastructure

compiler engineering

AI framework development

Education

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

Master's degree in related fields

PhD in related fields

Tools

ONNX

PyTorch

MLIR

TVM

Job description

Qualcomm is seeking an experienced compiler engineer to join the Qualcomm AI Hub Compiler team in Santa Clara, CA. You will design and maintain the end-to-end compilation pipeline while ensuring models compile correctly and efficiently across multiple backends.

The ideal candidate should have strong proficiency in Python and C++, as well as experience in ML infrastructure or compiler engineering. This position offers a competitive salary range from $160,500 to $240,700, along with bonuses and RSU grants.