Openings

Computer Vision Engineer ๐ŸŒ

Responsibilities

  • EfficientDet-Lite ๊ธฐ๋ฐ˜ ์˜จ๋””๋ฐ”์ด์Šค ๊ฐ์ฒด ์ธ์‹ ๋ชจ๋ธ ์ „์ด ํ•™์Šต ๋ฐ ๊ณ ๋„ํ™”
    Fine-tune and enhance on-device object detection models based on EfficientDet-Lite through transfer learning.
     

  • ๋น ๋ฅด๊ณ  ์ •ํ™•ํ•œ ์‚ฌ๋ฌผ ์ธ์‹์— ์ง‘์ค‘ํ•œ ์„ฑ๋Šฅ ํŒŒ์ธ ํŠœ๋‹
    Optimize model performance with a focus on fast and accurate object detection.
     

  • ์ง‘ ์•ˆ ์‚ฌ๋ฌผ ํƒ€๊ฒŸ ์ปค์Šคํ…€ ๋ฐ์ดํ„ฐ์…‹ ์ˆ˜์ง‘ ํŒŒ์ดํ”„๋ผ์ธ ๊ตฌ์ถ• ๋ฐ ๋ผ๋ฒจ๋ง ๊ด€๋ฆฌ
    Build and maintain custom data collection pipelines and labeling workflows for household object datasets.
     

  • ๋ชจ๋ฐ”์ผ ํ™˜๊ฒฝ์— ๋งž์ถ˜ ๋ชจ๋ธ ์‚ฌ์ด์ฆˆ INT8 ์–‘์žํ™” ๋ฐ ๋ฐœ์—ด/๋ฉ”๋ชจ๋ฆฌ ์ œ์–ด ์ตœ์ ํ™”
    Optimize model size using INT8 quantization and improve thermal and memory efficiency for mobile environments.
     

  • ์ž„๊ณ„๊ฐ’ ์กฐ์ •์„ ํ†ตํ•œ AR ๋ Œ๋”๋ง ์•ˆ์ •์„ฑ ํ™•๋ณด
    Improve AR rendering stability by optimizing detection confidence thresholds and inference parameters.

 

Qualifications

  • ๊ฐ์ฒด ์ธ์‹ ๋ชจ๋ธ(YOLO, MediaPipe, EfficientDet ๋“ฑ) ์ „์ด ํ•™์Šต ๋ฐ ํŠœ๋‹ ๊ฒฝํ—˜ ์žˆ์œผ์‹  ๋ถ„
    Experience with transfer learning and fine-tuning object detection models such as YOLO, MediaPipe, EfficientDet, or similar architectures.
     

  • TFLite, ONNX ๋“ฑ์„ ํ™œ์šฉํ•œ ๋ชจ๋ฐ”์ผ/์—ฃ์ง€ ๋””๋ฐ”์ด์Šค ๋ชจ๋ธ ๋ฐฐํฌ ๋ฐ ์ถ”๋ก  ๊ฒฝํ—˜์ด ์žˆ์œผ์‹  ๋ถ„
    Hands-on experience deploying and running inference with deep learning models on mobile or edge devices using frameworks such as TensorFlow Lite (TFLite) and ONNX Runtime.
     

  • PyTorch, TensorFlow ๋“ฑ ๋”ฅ๋Ÿฌ๋‹ ํ”„๋ ˆ์ž„์›Œํฌ ํ™œ์šฉ์— ๋Šฅ์ˆ™ํ•˜์‹  ๋ถ„
    Proficiency in deep learning frameworks such as PyTorch and TensorFlow.
     

  • ์˜จ๋””๋ฐ”์ด์Šค ํ™˜๊ฒฝ์—์„œ์˜ ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ ์ตœ์ ํ™” ์ดํ•ด๋„๊ฐ€ ์žˆ์œผ์‹  ๋ถ„
    Strong understanding of deep learning model optimization techniques for on-device deployment.
     

  • ์นด๋ฉ”๋ผ ๋น„์ „ ๊ธฐ๋ฐ˜์˜ AR ์• ํ”Œ๋ฆฌ์ผ€์ด์…˜ ํ”„๋กœ์ ํŠธ ์ฐธ์—ฌ ๊ฒฝํ—˜์ด ์žˆ์œผ์‹  ๋ถ„
    Experience developing or contributing to camera visionโ€“based AR applications.
     

  • ์ปดํ“จํ„ฐ ๋น„์ „ ์„/๋ฐ•์‚ฌ ํ•™์œ„ ์†Œ์ง€์ž ํ˜น์€ ๊ด€๋ จ ๋ถ„์•ผ ์‹ค๋ฌด ๊ฒฝ๋ ฅ์ž
    Master's or Ph.D. degree in Computer Vision or a related field, or equivalent industry experience.

 

Tech Stack

Python, PyTorch / TensorFlow, TFLite, ONNX Runtime, OpenCV

๋Œ“๊ธ€์€ ํšŒ์›๋งŒ ์ž‘์„ฑํ•  ์ˆ˜ ์žˆ์–ด์š”