Back
Strong employer and mid-level metro role raise competition; niche embedded GenAI skills moderately limit applicant pool.
Specialized on-device ML, SoC, SIMD and kernel expertise makes cross-industry transferability limited.
Explicit 6+ years plus mandatory embedded ML, C/C++, quantization, and hardware accelerator expertise increase strictness.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Lead development and commercialization of Qualcomm AI Runtime (QAIRT) SDK on Qualcomm SoCs specifically for on-device GenAI model inference.
Optimize deployment of large AI models (LLMs, LVMs) leveraging Qualcomm heterogeneous computing hardware to maximize inference speed and minimize power consumption.
Collaborate with cross-functional teams to push performance limits of AI inferencing on edge devices, focusing on C/C++ software stack management and GenAI advancements.
Master's or Bachelor's degree in Computer Science or equivalent.
6+ years of relevant software development experience.
Strong experience in C/C++ programming with design patterns and OS concepts.
Knowledge of Generative AI models (LLM, LVM), AI hardware acceleration optimization, and scripting in Python.
Experienced in deploying and optimizing large-scale AI inferencing software on embedded edge systems or SoCs.
Demonstrates deep understanding of AI model internals (self-attention, quantization) and hardware acceleration techniques for CPU/GPU/NPU.
Proficient in multi-language development environments, with familiarity in Linux/Windows, and AI frameworks (PyTorch, TFLite, ONNX).