Senior Staff AI/ML Inference Engineer – Graph & Runtime Ops

Qualcomm; San Diego (CA); On-site; USD 158,000 - 238,000; Full time

Job summary

Qualcomm Technologies, Inc. in San Diego invites applications for a Staff or Senior Staff Software Engineer on the Qualcomm AI Stack SDK Software team.

You will design, develop, and deliver advanced AI/ML software solutions for generative AI inference on Snapdragon platforms. The role emphasizes model optimization, quantization, graph transformations, and runtime execution across ONNX Runtime, ExecuTorch, and TFLite/LiteRT frameworks, working with cross‑functional teams and mentoring junior

Qualifications

• Hands-on AI/ML software development experience.
• Experience with inference or model optimization.
• Strong grounding in transformers and deep learning basics.

Responsibilities

• Convert, optimize, and deploy AI models from PyTorch and ONNX for efficient inference on Snapdragon.
• Design and implement graph transformations and optimization in AI runtimes such as ONNX Runtime, ExecuTorch, and QA Stack SDK.
• Apply quantization and performance optimization to improve latency, throughput, memory usage, and power efficiency.
• Work at the forefront of generative AI across attention mechanisms, MoE, LoRA, and speculative decoding.
• Collaborate with ML Research to prototype features and integrate into SDK solutions.
• Debug complex issues across models, runtime, OS, compiler and hardware with QA and customers.
• Deliver new features to the Qualcomm AI Stack SDK and participate in design/code reviews.
• Mentor junior engineers and drive execution across multiple initiatives.

Skills

Python

C/C++

PyTorch

ONNX

AI/ML fundamentals

Transformers

Inference optimization

Debugging

Education

Bachelor's degree in CS/related

Master's degree in CS/related

PhD in CS/related

Tools

ONNX Runtime

ExecuTorch

TFLite LiteRT

QAIRT SDK

QNN

Job description

Qualcomm Technologies, Inc. in San Diego invites applications for a Staff or Senior Staff Software Engineer on the Qualcomm AI Stack SDK Software team.

You will design, develop, and deliver advanced AI/ML software solutions for generative AI inference on Snapdragon platforms. The role emphasizes model optimization, quantization, graph transformations, and runtime execution across ONNX Runtime, ExecuTorch, and TFLite/LiteRT frameworks, working with cross‑functional teams and mentoring junior