Staff ML Compiler Engineer — On-Device AI Pipelines

Qualcomm Innovation Center, Inc.; Santa Clara (CA); On-site; USD 174,000 - 261,000; Full time

Job summary

Qualcomm Technologies, Inc. is seeking a skilled Compiler Engineer to join the Qualcomm AI Hub Compiler team in Santa Clara, CA.

You will design and maintain end-to-end ML compilation pipelines, collaborate across CPU, GPU, and NPU backends, and advance automated CI/CD workflows for model onboarding. The role requires a BS in CS/Engineering or related field with 4+ years in hardware/software/systems, plus strong Python/C++ and ML compiler experience.

Qualifications

• Bachelor's degree in Computer Science, Engineering, Information Systems, or related field with 4+ years of relevant experience.
• Experience in hardware/software/systems engineering and model compilation workflows.
• Strong background in ML infrastructure, compilers, or related performance optimization.

Responsibilities

• Design, develop, and maintain end-to-end ML compilation pipelines for Qualcomm AI Hub Workbench.
• Build ONNX-based and PyTorch compilation paths and ensure compatibility across runtimes.
• Collaborate with QAIRT and QNN teams to optimize execution on CPU, GPU, and NPU backends.

Skills

Hardware Engineering

Software Engineering

Systems Engineering

ML/AI fundamentals

Education

Bachelor's degree in CS/Engineering/IS

Tools

PyTorch

ONNX

ONNXRuntime

MLIR

TVM

LiteRT

QAIRT

QNN

Job description

Qualcomm Technologies, Inc. is seeking a skilled Compiler Engineer to join the Qualcomm AI Hub Compiler team in Santa Clara, CA.

You will design and maintain end-to-end ML compilation pipelines, collaborate across CPU, GPU, and NPU backends, and advance automated CI/CD workflows for model onboarding. The role requires a BS in CS/Engineering or related field with 4+ years in hardware/software/systems, plus strong Python/C++ and ML compiler experience.