Back
Tier-1 brand, mid-level seniority requirement, and metro location increase candidate competition despite niche embedded ML skills.
Requires embedded ML and SoC optimization expertise, making skills less transferable across industries.
Mandatory 6+ years, specialized embedded ML, C/C++, and hardware acceleration expertise create strict screening filters.
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.
Optimize and deploy large-scale C/C++ AI inference software stacks for edge devices using Qualcomm hardware.
Integrate and enhance Generative AI models (LLMs, LVMs) inference performance on-device leveraging heterogeneous computing capabilities.
Bachelor’s degree in Engineering, Computer Science or related field with 3+ years, OR Master’s with 2+ years, OR PhD with 1+ year relevant software development experience.
6+ years of professional software development experience, especially in C/C++ programming and OS concepts.
Strong understanding of Generative AI models including LLMs, LVMs and concepts like self-attention, kv caching, and quantization.
Experience optimizing algorithms for AI hardware accelerators (CPU/GPU/NPU) and scripting skills in Python.
Experienced in integrating and optimizing AI inference engines on edge hardware platforms, especially Qualcomm chipsets.
Skilled in advanced C/C++ software engineering with knowledge of design patterns and system-level OS concepts.
Familiar with SIMD processor architecture, kernel development, and frameworks like llama.cpp, MLX, with preferred knowledge of PyTorch, TFLite, ONNX Runtime, and parallel computing languages (OpenCL, CUDA).