Engineer, Senior-Machine Learning, embedded, C++
Qualcomm IncorporatedMatch Score
Against your primary resumeLogin to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Protocol Intelligence
Data-driven signals on your job's competitivenessTier-1 brand, mid-level experience band, metro role and popular ML title increase candidate competition.
Embedded GenAI and SoC accelerator optimization are highly specialized, limiting cross-industry transferability.
Explicit 4+ years plus deep embedded ML, C/C++, quantization and accelerator expertise make shortlisting highly strict.
Job Description
Structured overview of role & requirementsAbout This Role
Lead development and commercialization of Qualcomm AI Runtime (QAIRT) SDK on Qualcomm SoCs focused on AI inferencing.
Optimize and deploy large C/C++ software stacks for generative AI models like LLMs and LVMs on-device leveraging Qualcomm heterogeneous computing.
Push performance limits of large AI models on edge devices combining software and hardware accelerator optimization.
Minimum Requirements
Bachelor's, Master's or PhD in Computer Science, Engineering, or related with 4+ years relevant software development experience.
Strong proficiency in C/C++ programming and design patterns, with experience in scripting languages like Python.
Solid understanding of generative AI models (LLM, LVM), floating/fixed-point operations, quantization, and AI hardware accelerator optimization.
Work Experience Required: Minimum 4 years in software development relevant to AI, embedded, or related fields.
Ideal Candidate Profile
Experienced in deploying and optimizing large-scale AI inferencing engines on embedded platforms or SoCs.
Strong technical mastery in C++/C and AI system architecture including SIMD and kernel development for hardware accelerators.
Familiarity with edge deployment of GenAI models, frameworks like llama.cpp or MLX, and working within globally distributed engineering teams.