Back
Tier-1 brand and metro hiring increase competition, but niche embedded ML specialization reduces applicant density.
Requires SoC, SIMD, kernel and embedded ML expertise, making skills highly industry- and domain-specific.
Explicit 6+ years plus mandatory embedded ML, C/C++ optimization, and hardware accelerator skills enforce strict filtering.
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 for Qualcomm SoCs focused on AI inferencing on edge devices.
Optimize and deploy large C/C++ software stacks implementing Generative AI models (LLMs, LVMs) using Qualcomm heterogeneous computing capabilities.
Push performance boundaries of on-device GenAI model inference leveraging hardware accelerators (CPU/GPU/NPU) and advanced AI model concepts (self-attention, quantization).
Bachelor's (with 6+ years), Master's (with 3+ years), or PhD (with 2+ years) in Engineering, Computer Science, or related field.
6+ years relevant software development experience, including strong C/C++ programming skills.
Knowledge of Generative AI models (LLM, LVM, LMMs), floating/fixed-point and quantization concepts, and optimization for AI hardware accelerators.
Proficiency in scripting with Python; experience with OS concepts and design patterns.
Experienced in deploying large-scale AI inference software on embedded systems and SoCs, particularly Qualcomm platforms.
Deep understanding of Generative AI architectures (Transformers, self-attention, caching) and edge deployment challenges.
Skilled in performance optimization on heterogeneous hardware and familiar with SIMD processor architecture, kernel development, and parallel computing frameworks (preferred).