Skip to main content

Intern – AI Model Efficiency (Quantization) System/Research Engineer at Qualcomm International Inc., Mexico Branch Office

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 benchmark accuracy, latency, throughput, and memory performance, prototype production-ready solutions, collaborate with global teams, and document findings. The role requires a current BS, MS, or PhD in a relevant field, Python proficiency, deep learning framework experience, and strong problem-solving and debugging skills; quantization, model compression, Triton, CUDA, and inference optimization are 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