Skip to main content

Intern – AI Model Efficiency (Quantization) System/Research Engineer at Qualcomm Technologies, Inc.

Department: Interim Engineering Intern - SW

Language
Setup
On-site
Location
Seoul
Type
Internship
Level
intern
Posted

Description

Qualcomm Korea YH is hiring an Interim Engineering Intern - Software in Seoul to research and develop low-bit quantization, model compression, efficient inference kernels, and evaluation pipelines for AI models deployed on Qualcomm edge hardware. The intern will implement and benchmark PTQ/QAT methods, profile latency, throughput, and memory performance, prototype production-ready solutions, and collaborate with global teams. The role requires a current BS, MS, or PhD in a relevant field, Python proficiency, deep learning framework experience, and strong debugging skills; knowledge of quantization, Triton, CUDA, and model profiling is preferred.

For job seekers

Ready to find a role that actually fits?

Upload your résumé, start a Job Search Thread, and let Metaintro rank real openings against your experience — then guide you from search to offer.

Match

Compare live roles against your current evidence.

Position

Turn proof projects into role-specific applications.

Improve

Use market feedback to keep the skill plan current.

Return to navigation