AI 應用程式開發工程師
Posted Updated
Description
About the Role:
We are looking for a hands-on LLM Application Engineer to build and deploy production-level AI applications. You will go beyond basic API calls to design complex AI systems, including Retrieval-Augmented Generation (RAG) chatbots and autonomous AI Agents. If you enjoy building scalable AI solutions from the ground up, writing clean backend code, and understanding the core mechanics of LLMs, we want you on our team!
Key Responsibilities:
- AI Application Development: Design, build, and deploy production-grade LLM applications, focusing on RAG systems and AI Agent architectures.
- Backend Engineering: Develop robust and high-performance API services using Python and the FastAPI framework.
- Data Processing Pipeline: Extract, clean, and process diverse forms of structured and unstructured data (text, documents, logs, etc.) to feed into LLM contexts.
- Semantic Search Integration: Utilize NoSQL databases to implement efficient vector embeddings and semantic search capabilities for our RAG systems.
- Agent Architecture: Construct AI agents leveraging the native capabilities of the LLM (e.g., function calling, reasoning loops).
Requirements:
- Solid experience in deploying AI applications in a production environment.
- Strong proficiency in Python and backend development with FastAPI.
- Deep understanding of the OpenAI SDK: Ability to build complex AI workflows and Agents purely using the OpenAI SDK (demonstrating a strong grasp of prompt engineering, tool use/function calling, and memory management without over-relying on heavy frameworks like LangChain).
- Hands-on experience with NoSQL databases (e.g., MongoDB, Elasticsearch, or dedicated Vector DBs) for semantic search.
- Proficient in Linux operations and server-side troubleshooting.
- Strong ability to handle and parse both structured (JSON, SQL, CSV) and unstructured data (PDFs, raw text, HTML).
關於此職位:
我們正在尋找一位具備強大實作能力的 LLM 應用工程師,負責開發並落地具備商業價值的(Production-level)AI 應用程式。您將不只是串接 API,而是需要從底層邏輯出發,設計包含 RAG (檢索增強生成) 聊天機器人與自主 AI Agent 的複雜系統。如果您熱衷於打造高效能的 AI 服務,並對 LLM 的核心運作機制有深入理解,歡迎加入我們!
主要職責:
- AI 應用落地: 設計、開發並部署 Production-level 的 LLM 應用,主導 RAG 系統與 AI Agent 的架構設計與實作。
- 後端服務開發: 使用 Python 與 FastAPI 框架,建構穩定、高效能的後端 API 服務。
- 資料萃取與處理: 處理各種結構化與非結構化資訊(如文件、網頁、日誌等),進行清洗與切塊(Chunking),以提供 LLM 精準的上下文。
- 語義搜索整合: 熟悉並運用 NoSQL 資料庫(如 MongoDB, Elasticsearch 或特定向量資料庫)進行 Vector Embedding 與高效的語義搜索(Semantic Search)。
徵才條件:
- 具備將 AI 應用推上線(Production)的實際經驗。
- 精通 Python 程式語言與 FastAPI 後端開發。
- 精通 OpenAI SDK: 具備強大的原生開發能力,能夠「單純使用 OpenAI SDK」從零搭建 AI Agent 應用(展現對 Function Calling/Tools、Context Window 管理的深刻理解,不過度依賴 LangChain 等高度封裝的框架)。
- 具備使用 NoSQL 資料庫建構語義搜索(Semantic Search)系統的實務經驗。
- 熟悉 Linux 系統操作、環境建置與問題排解。
- 具備處理結構化(JSON, CSV)與非結構化(PDF, 純文字等)資料的豐富經驗。