Embedded AI Engineer

Qualcomm’s Embedded AI team in San Diego is hiring a Senior Embedded AI Engineer to develop and deploy machine learning inference solutions on our Snapdragon and Qualcomm IoT platforms. You will work on optimizing neural network models for on-device execution using Qualcomm’s AI Engine — a heterogeneous compute architecture spanning CPU, GPU, DSP, and NPU cores. Your work enables real-time AI applications in camera, audio, automotive, and industrial IoT domains.

In this role, you will implement low-level inference runtimes, optimize operator kernels for ARM Cortex-A and Hexagon DSP targets, and build tooling for model quantization and profiling. You will collaborate with ML researchers to translate graph-level algorithms into efficient embedded implementations, and work with platform teams to integrate inference pipelines into production firmware. Strong C/C++ and Python skills are required, along with demonstrated experience in embedded systems programming and performance optimization on resource-constrained devices.

We are looking for engineers who understand both the ML and embedded sides of the stack. Experience with TensorFlow Lite Micro, ONNX Runtime, Qualcomm SNPE/QNN, or similar embedded inference engines is highly desirable. If you want to put AI into billions of devices, this is the place to do it.

• Health, dental, and vision insurance
• 401k matching
• Tuition reimbursement
• On-site cafeteria and fitness center