新竹市5年以上碩士以上
【職務說明】 我們是一條以AI 驅動的先進封裝產線,專注於 MicroLED 與 VCSEL 的巨量轉移、檢測與修補,致力於打造下一世代的 先進顯示技術與矽光子應用。我們正在尋找一位具備頂尖 AI 專業與智慧製造導入經驗的領導者,帶領團隊建構以資料為核心的決策平台,全面提升製程效率、良率與品質穩定性,加速 AI 技術在封裝產線中的實際落地與規模化應用。
【工作內容】
1. 制定 AI 導入策略,聚焦於 MicroLED / VCSEL 巨量轉移、瑕疵檢測、重工修補與製程參數最佳化等核心環節。
2. 領導資料科學家、AI/ML 工程師與軟體開發團隊,推動跨部門 AI 研發與部署。
3. 深度解析封裝產線之異質數據(如機台 log、SPC、AOI 影像、MES 資訊),建構可解釋性高的分析架構。
4. 開發高效能之缺陷分類、良率預測、自動瑕疵標註、根因分析模型,並落地於產線即時應用。
5. 應用強化學習於巨量轉移製程參數之動態調整與優化,突破微組件對位與轉移良率瓶頸。
6. 導入大型語言模型(LLM)與視覺語言模型(VLM),應用於智慧良率歸因、報表生成與製程決策輔助。
7. 建立並優化 MLOps 架構與模型版本管理系統,支援模型從研發到部署的全生命週期。
8. 推動公司內部 AI 能力建設,協助夥伴部門建立資料思維與基本技術知識。
9. 與製造、測試、IT、設備等部門緊密協作,確保模型輸出能轉化為實際效益。
Job Description:
We are seeking a visionary leader with top-tier expertise in Artificial Intelligence and a proven track record in smart manufacturing implementation. In this role, you will lead the development of a data-driven intelligent manufacturing decision platform focused on MicroLED process optimization, production efficiency, yield maximization, and automated quality assurance. You will be responsible for the strategic planning of AI technology integration, cross-functional collaboration, advanced model development and deployment, and ensuring the successful adoption of AI innovations that significantly enhance manufacturing performance and product quality.
Key Responsibilities:
1.Formulate AI strategies and roadmaps for MicroLED smart manufacturing, driving cutting-edge research, project planning, and prioritization.
2.Lead and develop a multidisciplinary AI team, including data scientists, AI/ML engineers, and software developers.
3.Perform in-depth analysis and mining of complex production data (e.g., equipment logs, sensor data, SPC, MES systems) to uncover deep insights and correlations.
4.Spearhead the development and optimization of advanced machine learning and deep learning models for defect detection, automated quality control, anomaly prediction, and root cause analysis.
5.Drive intelligent process optimization for key manufacturing steps (e.g., mass transfer) using advanced algorithms such as reinforcement learning to achieve dynamic parameter tuning and breakthrough efficiency gains.
6.Explore and implement applications of large language models (LLMs) and vision-language models (VLMs) for yield analysis, process knowledge extraction, and decision-making support.
7.Plan and implement efficient MLOps systems and lifecycle management for AI models.
8.Build internal AI capabilities and promote cross-functional AI thinking through education and training initiatives.
9.Collaborate closely with manufacturing, equipment, IT, and quality departments to ensure successful deployment and realization of AI solutions on the production floor.