Senior AI Tools Engineer: Quantization & Inference

Qualcomm; Raleigh, Northern (NC, KY); Hybrid; USD 127,000 - 190,000; Full time

Job summary

Qualcomm Technologies, Inc. is seeking a Sr Software Engineer focused on AI Tools and Quantizer development in Raleigh, NC. You will design and implement quantization tooling within AISW Tools to enable fast, power-efficient neural network inference on Snapdragon platforms.

The role requires strong Python/C++ development, ML theory knowledge, and experience with PyTorch, TensorFlow, ONNX, or JAX. You will collaborate with global teams and mentor junior engineers while driving performance

Qualifications

• Bachelor's degree in Computer Science, Engineering, Information Systems, or related field.
• Master's degree/PhD preferred for advanced roles.
• 4+ years of software development with Python and/or C/C++.

Responsibilities

• Collaborate with cross-functional AI Software teams to optimize QAIRT SDK and AI model inference on Qualcomm accelerators.
• Validate and optimize quantized models through detailed testing and performance analysis.
• Debug complex issues, perform root cause analysis, and ensure high system reliability.
• Lead design/code reviews and mentor junior team members, adopting agentic AI workflows to automate experiments.

Skills

Python

C/C++

ML theory

Communication skills

PyTorch

TensorFlow

ONNX

JAX

Education

Bachelor's degree in CS/Engineering

Master's degree preferred

Tools

AIMET

TorchAO

Job description

Qualcomm Technologies, Inc. is seeking a Sr Software Engineer focused on AI Tools and Quantizer development in Raleigh, NC. You will design and implement quantization tooling within AISW Tools to enable fast, power-efficient neural network inference on Snapdragon platforms.

The role requires strong Python/C++ development, ML theory knowledge, and experience with PyTorch, TensorFlow, ONNX, or JAX. You will collaborate with global teams and mentor junior engineers while driving performance