Staff Software Engineer, AI Runtime
Core
Design and create high-performance software using modern C++ to optimize GenAI model execution on-device utilizing Hexagon DSPs.
Role type
Staff Software Engineer (AI Runtime)
Builds
Qualcomm AI Runtime SDK features for on-device GenAI inference
Domain
Embedded systems, Generative AI, High-performance computing
Deliverable
production ML models
Required skills
Modern C++, Multithreading, Embedded firmware development, Hexagon DSP SDK, Cross-compiler toolchains, JIT technologies, Low-level OS/hardware interaction, Qualcomm FastRPC, Windows MCDM drivers, Qualcomm AI Stack (QNN, SNPE, QAIRT), TensorFlow, PyTorch, ONNX
Preferred skills
Masters degree in CS/CE/EE
Technologies
C++, Hexagon DSP, Android, Embedded Linux, Windows, QNX, Git, JIRA, REST
Responsibilities
Develop high-performance C++ software for Qualcomm AI Runtime SDK, Optimize GenAI model inference latency and power on Hexagon DSPs, Lead feature development for the SDK, Provide analysis on system and model deployment designs, Implement and optimize ML operations on Hexagon DSP systems, Create tools and workflows for GenAI chip and system analysis
Seniority
Staff, hands-on IC with strategic influence
