Jimin Ha

SW Engineer at Intel Corporation

San Diego, California, United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Jimin Ha is a seasoned embedded software engineer and manager with over 15 years of experience building mobile and embedded platforms, now applying computer vision and deep learning to autonomous driving and smart home systems at Intel. He has led end-to-end product development from requirements to release across Android, modem/driver layers, and multimode cellular systems (CDMA/UMTS/LTE), blending low-level protocol expertise with modern ML toolchains like TensorFlow and Movidius. At Qualcomm and Motorola he drove Android bring-up, carrier-specific features, and system-selection stability for complex multimode devices, and pioneered Motorola’s first automated Android release pipeline. Known for translating customer requirements into robust specifications, he pairs hands-on coding in C/C++ and Linux with program-level leadership and debugging (T32, Gerrit, Clearcase). Based in San Diego, he combines deep telecom protocol knowledge with practical ML deployment experience—an atypical bridge between modem firmware and applied computer vision.
code9 years of coding experience
job13 years of employment as a software developer
bookBachelor of Science (BS), Computer Science, Cum Laude, Bachelor of Science (BS), Computer Science, Cum Laude at Sogang University
bookUnnam high school
languagesKorean
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (25)

transformers10
pytorch10
onnx10
bert10
fine-tuning10
openvino9
amd9
llm9
inference9
llama9
mxnet9
tensorflow9
deep-learning9
openai9
gpt9

Programming languages (2)

C++Python

Github contributions (5)

github-logo-circle
jiminha/vllm-gaudi

Sep 2025 - May 2026

Community maintained hardware plugin for vLLM on Intel Gaudi
Contributions:46 pushes, 15 branches in 8 months
jiminha/vllm-fork

Apr 2025 - Aug 2025

A high-throughput and memory-efficient inference and serving engine for LLMs
Contributions:3 pushes, 4 branches in 3 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial