工作內容
1. 設計、實施和維護本地人工智能推理服務器。
2. 跨職能團隊合作，確保無縫項目交付。
3. 維護和提高我們的服務/平台的可靠性和可擴展性。
4. 實施最佳實踐和行業標準以優化平台性能。
5. 及時有效地排除和解決問題。
6. 記錄知識共享和未來參考的流程和程序。
相關資歷
1. 通過盛行的 Web 框架開發（Flask、Django 等），在 RESTful API 開發方面擁有經過驗證的實踐專業知識。
2. 熟悉 Linux 上的 Docker 和 Git 技術。
3. 熟悉網絡和瀏覽器技術。
4. 精通 Python 並具有豐富的實踐經驗（必要條件）。
5. 具有數據庫經驗（PostgreSQL、MongoDB 等）。
6. 具有人工智能基礎設施、開發和設計的最佳原則、實踐和模式的經驗。
7. 有GCP 和相關機器學習服務的經驗。
加分項目-
1. 具 CI/CD 經驗（例如 Gitlab、Github、Drone）。
2. 對技術充滿熱情，了解如何位具體的業務挑戰構建技術解決方案。
※ MLOps方面
1. 有機器學習自動化、MLOps 和相關工具（MLflow、Airflow、Kubeflow 等）的經驗
2. 具MLOps 的實踐經驗，包括在雲端部署和管理 AI/ML 模型（例如 Google Cloud Platform 等）。
※DL方面
1. 具有電烤視覺模型開發經驗。
2. 對電腦視覺技術和深度學習算法有一定的了解，對圖像處理方法有深入的了解。
3. 具Python編程專業知識，以及深度學習庫（Pytorch、TensorFlow等）的經驗
4. 有深度學習模型加速開發經驗（TensorRT、Onnxruntime、OpenVINO等）
5. 有使用K8s體驗。
Job description
1. Design, implement, & maintain the on-premise AI inference servers.
2. Collaborating with cross-functional teams to ensure seamless project delivery.
3. Maintaining and improving the reliability, and scalability of our services/platforms.
4. Implementing best practices and industry standards to optimise platform performance
5. Troubleshooting and resolving issues in a timely and efficient manner.
6. Documenting processes and procedures for knowledge sharing and future reference.
Qualifications Experience
1. Proven hands-on expertise in RESTful API developments via popular web framework developments (Flask, Django, etc).
2. Familiarity with Docker, and Git technologies on Linux.
3. Familiarity with web and browser technologies.
4. Advanced proficiency and intense hands-on experience with Python (Mandatory).
5. Experience with databases (PostgreSQL, MongoDB, etc).
6. Experience with the best principles, practices, and patterns of AI infrastructure, development, and design.
7. Experience in GCP and associated machine learning services.
Pluses-
1. Experience with CI/CD (e.g., Gitlab, Github, and Drone).
2. Passion for technology and understanding of how to build technology solutions for concrete business challenges.
[About MLOps parts]
1. Experience in implementing ML automation, MLOps and related tools (MLflow, Airflow, Kubeflow, etc)
2. Hands-on experience with MLOps, including deploying and managing AI/ML models on the cloud (e.g., Google Cloud Platform, etc.).
[About DL parts]
1. Experience in computer vision model development.
2. Soft understanding of computer vision techniques and algorithms of deep learning, and a solid understanding of image processing methods.
3. Expert knowledge of Python programming, and experience with deep learning libraries (Pytorch, TensorFlow, etc)
4. Experience in deep learning model accelerating development (TensorRT, Onnxruntime, OpenVINO, etc)
5. Experience with K8s.
