Back
Medium due to Tier-1 brand and metro location but specialized edge ML and low-level skills required.
High because role demands specialized edge inference, SIMD/kernel development and hardware-accelerator optimization skills.
High because the JD mandates 6+ years plus specific C/C++, accelerator, quantization and kernel expertise.
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 for edge AI inferencing.
Optimize performance of large generative AI models (LLMs, LVMs) running on Qualcomm heterogeneous computing platforms with efficient power usage.
Deploy and maintain large C/C++ software stacks utilizing best practices and integrate generative AI models on-device without cloud dependency.
Bachelor's degree in Engineering, Information Systems, Computer Science, or related field with 6+ years relevant software development experience.
Strong proficiency in C/C++ programming, design patterns, and OS concepts; scripting skills in Python.
Solid understanding of generative AI models (LLM, LVM, LMMs), including self-attention, cross attention, kv caching, floating-point/fixed-point and quantization.
Experience optimizing algorithms for AI hardware accelerators (CPU/GPU/NPU).
Experienced AI inferencing expert familiar with deploying large-scale C/C++ software stacks and integrating generative AI on edge devices.
Deep understanding of advanced AI model architectures (Transformers, LLMs, LVM) and edge deployment challenges.
Technical breadth spanning SIMD processor architecture, kernel development, Linux/Windows environment, and familiarity with AI frameworks like llama.cpp, MLX, MLC, PyTorch, TFLite, ONNX Runtime.