KT, VISION AI Research Engineer (2018.12 ~ )
Researched and Developed Vision AI technologies. Used Python and C/C++, and deployed a model using Pytorch, Onnx and TensorRT, Docker, Triton Inference Server, Kubernetes
- Developed Large Vision Model Weight Lightening and Optimiation (2023.1 - current)
- Developed Stable Diffusion Model Weight Lightening and Optimiation (2023.1 - current)
- Developed Gesture Recognition using Hand Keypoints (2022.1 - 2022.12)
- Developed Food Detection (2021.9 - 22.08)
- Developed Vision OpenAPI Server(2021.11 - current)
- Researched vision model Optimization and Compression for Edge Device (2021.08 - 2021.11)
- Researched and developed Face Landmark Detection(2020.08 - 2021.07)
- Developed Make KT’s Face and Mask Face Recognition Library (2020.04 - 2021.07)
- Researched and developed Face Eyes Detection(2020.04 - 2021.06)
- Researched and developed Face and Mask Face Detection(2020.01 - 2021.12)
- Developed Face Blur Classification (2020.01 - 2020.03)
- Researched and developed Face Attribution Classification for glasses, masks, and hats (2019.01 - 2019.12)