職位描述
Job Profile: Engineering > ETS
Job Responsibilities:
Develop deep learning-based vision algorithms, optimize and debug models, and participate in machine vision software development.
Design and implement new vision algorithms according to project requirements, focusing on the development and optimization of core algorithms in the machine vision domain.
Execute machine vision projects on-site at customer locations, including data collection, testing, verification, and debugging.
Complete visual software development, engineering implementation, and iterative optimization for projects, products, and solutions.
Prepare and update relevant technical documentation.
Perform tasks assigned by supervisors and other leaders.
Job Requirements:
Bachelor’s degree or above in Computer Science, Image Processing, Deep Learning, Artificial Intelligence, or related fields, with over 3 years of experience in computer vision algorithm development.
Proficient in C++/C#/Python, with a solid theoretical foundation in algorithms; skilled in image processing fundamentals and familiar with algorithm libraries such as OpenCV and Halcon.
Familiar with common deep learning models, including object detection, image segmentation, object classification, and OCR.
Proficient in at least one deep learning framework (e.g., PyTorch, PaddlePaddle).
Experience in unsupervised learning, zero-shot learning, ViT, defect detection, and character recognition is preferred.
Prior experience in deploying deep learning-based visual inspection projects in industrial settings is a plus.
崗位職責(zé):
負(fù)責(zé)深度學(xué)習(xí)視覺算法的開發(fā)、模型優(yōu)化與調(diào)試,以及機(jī)器視覺產(chǎn)品軟件開發(fā)。
根據(jù)項(xiàng)目需求,設(shè)計(jì)并開發(fā)新的視覺算法,完成機(jī)器視覺及圖像處理核心算法的實(shí)現(xiàn)與優(yōu)化。
負(fù)責(zé)機(jī)器視覺項(xiàng)目在客戶現(xiàn)場的實(shí)施,包括數(shù)據(jù)采集、測試驗(yàn)證及調(diào)試工作。
完成項(xiàng)目、產(chǎn)品及解決方案的視覺軟件開發(fā)、工程化及優(yōu)化迭代。
編制并更新相關(guān)技術(shù)文檔。
完成上級(jí)及其他領(lǐng)導(dǎo)交辦的工作任務(wù)。
任職要求:
本科及以上學(xué)歷,計(jì)算機(jī)、圖像處理、深度學(xué)習(xí)、人工智能等相關(guān)專業(yè),具備3年以上圖像算法開發(fā)經(jīng)驗(yàn)。
精通C++/C#/Python之一,具備扎實(shí)的算法理論基礎(chǔ),熟練掌握?qǐng)D像處理基礎(chǔ)知識(shí)及相關(guān)算法庫(OpenCV、Halcon)。
熟悉深度學(xué)習(xí)常見模型(目標(biāo)檢測、圖像分割、物體分類、OCR等)。
掌握至少一種深度學(xué)習(xí)框架(如PyTorch、PaddlePaddle)。 有非監(jiān)督學(xué)習(xí)、零樣本學(xué)習(xí)、ViT、缺陷檢測、字符識(shí)別等相關(guān)經(jīng)驗(yàn)者優(yōu)先。
有工業(yè)領(lǐng)域深度學(xué)習(xí)視覺檢測項(xiàng)目落地經(jīng)驗(yàn)者優(yōu)先。