- Co-researcher AI 代理大腦開發： 設計並實作具備複雜研發任務拆解、長期記憶與跨領域邏輯推理能力的 Co-researcher 核心架構。確保 AI 代理能自主理解企業業務痛點，主動制定研究計畫、調用各類分析工具，並綜合歸納出具策略意義的洞察報告。
- ML Agent 研發與自動化機器學習 (AutoML) 整合： 開發專注於機器學習任務的 ML Agent，使其能自主執行資料預處理、特徵工程 (Feature Engineering)、模型訓練、超參數調優與模型評估。將傳統 ML 框架（如 Scikit-learn, XGBoost, PyTorch）無縫封裝為 AI 代理可靈活調用的工具 (Tools/Skills)。
- 大數據生態系與 AI 管線深度結合： 與資料工程及後端團隊緊密合作，利用 ETL 與 Apache Spark 等工具建立自動化的資料萃取與清洗管線。確保 Co-researcher 與 ML Agent 能即時存取、分析並處理儲存於 Hadoop 與 Iceberg 中的海量結構化與非結構化企業級數據。
- 進階 AI 檢索系統與向量工程： 針對企業內部專有文獻、研究報告與海量日誌，設計並優化檢索系統。建置高效能的向量資料庫 (如 Milvus, Qdrant)，實作混合檢索、語意路由與重排序策略，為 Co-researcher 提供精準的知識檢索底層支援。
- 地端大語言模型 (LLM) 部署與推論優化： 針對無法連網的高資安地端環境，負責開源大語言模型的評估與私有化部署。利用 vLLM 等推論引擎進行模型量化與效能調優，確保 Co-researcher 在邊緣或地端伺服器上能維持極低的延遲與高吞吐量。
- AI 與 ML 資訊安全防護實作： 將資安思維融入 AI 與 ML 模型開發的每個環節。實作企業級資料脫敏、個人機密資訊 (PII) 過濾機制，防範模型毒化 (Data Poisoning) 與提示詞注入 (Prompt Injection)，確保 AI 代理的所有研究行為與資料存取絕對符合企業權限規範 (RBAC) 與零信任架構。
- Co-researcher Agent "Brain" Development: Build the core architecture for decomposing complex R&D tasks, long-term memory, and cross-domain reasoning, so the Agent can grasp enterprise pain points, formulate research plans, invoke analytical tools, and synthesize strategic insight reports.
- ML Agent and AutoML Integration: Build an ML Agent that autonomously runs data preprocessing, feature engineering, model training, hyperparameter tuning, and evaluation, wrapping traditional ML frameworks (Scikit-learn, XGBoost, PyTorch) into tools/skills it can flexibly invoke.
- Big-Data Ecosystem and AI Pipeline Integration: Partner with data engineering and backend teams to build automated extraction and cleansing pipelines (ETL, Apache Spark), enabling the Co-researcher and ML Agent to access and process massive structured and unstructured data in Hadoop and Iceberg in real time.
- Advanced AI Retrieval and Vector Engineering: Design and optimize retrieval over proprietary literature, reports, and logs; build high-performance vector databases (Milvus, Qdrant) with hybrid retrieval, semantic routing, and re-ranking for precise knowledge retrieval.
- On-premise LLM Deployment and Inference Optimization: Evaluate and privately deploy open-source LLMs for offline, high-security environments, using engines such as vLLM for quantization and tuning to keep latency low and throughput high on edge or on-premise servers.
- AI and ML Security: Embed security into every stage of development—enterprise-grade data masking and PII filtering, defense against data poisoning and prompt injection—ensuring all Agent research and data access comply with enterprise permissions (RBAC) and zero-trust architecture.
- 資訊工程、資料科學、統計學、應用數學或相關領域學士以上學位。
- 具備 1 年以上軟體工程與 AI/資料科學開發經驗，其中必須包含豐富的機器學習 (Machine Learning) 與大型語言模型 (LLM) 落地實戰經驗。
- 精通 Python，具備深厚的資料科學與 ML 開發生態系底蘊（熟悉 Pandas, NumPy, Scikit-learn, XGBoost/LightGBM，以及 PyTorch 或 TensorFlow 深度學習框架）。
- 熟悉當前主流的大型語言模型應用與 Agent 框架，具備開發多代理協作系統 (Multi-Agent Orchestration) 的能力。
- 具備將 ML 模型部署至生產環境 (MLOps) 的實務經驗，深刻理解模型生命週期管理、特徵庫 (Feature Store) 與模型監控機制。
- 熟練掌握向量資料庫的底層邏輯與操作，具備處理千萬級別以上向量數據的索引與檢索優化經驗。
- 理解巨量資料處理與分散式系統概念，能夠與工程團隊針對 Hadoop / Spark 資料管線進行深度的架構討論與整合。
- Bachelor's degree or above in Computer Science, Data Science, Statistics, Applied Mathematics, or a related field.
- 1+ years in software engineering and AI/data science, including hands-on real-world deployment of Machine Learning (ML) and Large Language Models (LLMs).
- Proficient in Python with deep grounding in the data science and ML ecosystem.
- Familiar with mainstream LLM applications and Agent frameworks, able to build multi-agent orchestration systems.
- Practical MLOps experience deploying ML models to production, with solid grasp of model lifecycle management, feature stores, and monitoring.
- Strong command of vector database internals, with index and retrieval optimization experience for tens of millions of vectors or more.
- Understanding of big-data processing and distributed systems, able to drive architecture discussions and integration on Hadoop / Spark pipelines.
第一次面試可以遠端進行， 第一次面試需要 Onsite進行。
- 具備開發自主研發代理 (Autonomous Research Agents) 或自主寫扣代理 (Coding Agents) 的實際專案經驗者（如曾深入研究或二度開發開源專案）極度加分。
- 熟悉 ML 基礎設施與管線編排工具（如 MLflow, Kubeflow, Apache Airflow），能將 ML Agent 整合進企業現有的 MLOps 流程中。
- 具備於企業地端 (On-premise) 或封閉網路 (Air-gapped) 環境中建置 AI 或大數據產品的成功實績。
- 具備大型開源模型微調 (Fine-tuning) 經驗，熟悉 PEFT、LoRA 等參數高效微調技術，能針對特定企業研發領域知識客製化模型能力。
- 熟悉 Apache Iceberg 與分散式運算架構，能獨立撰寫 PySpark 腳本協助 Co-researcher 處理底層大數據。
- 熟悉 TypeScript 與 Node.js 後端開發，能夠無縫對接後端 API，理解現代化系統架構與微服務容器化 (Docker, Kubernetes) 部署。
- 具備半導體、材料科學、物理模擬或科學計算等相關領域背景或產業知識者佳（歡迎但非必要）。
- Hands-on experience developing Autonomous Research Agents or Coding Agents (e.g., deep study of or contributions to open-source projects) is a major plus.
- Familiar with ML infrastructure and orchestration tools, able to integrate the ML Agent into existing enterprise MLOps workflows.
- Proven track record building AI or big-data products in enterprise on-premise or air-gapped environments.
- Experience fine-tuning large open-source models with parameter-efficient techniques (PEFT, LoRA) for specific enterprise R&D domains.
- Familiar with Apache Iceberg and distributed computing, able to write PySpark scripts to help the Co-researcher process big data.
- Familiar with TypeScript and Node.js backend development, modern system architecture, and microservice containerization (Docker, Kubernetes).
- Background or industry knowledge in semiconductors, materials science, physics simulation, or scientific computing is a plus (welcome but not required).
1. 休假制度：年假
2. 獎金福利制度：年終獎金、績效獎金、專利與創新獎勵
3. 專業發展與學習支持：
a. 提供線上或實體課程補助、證照考試費用補貼。
b. 定期舉辦相關講座、工作坊以及讀書會。
c. 支持員工進行創新專案，提供額外的經費與資源。
4. 成長空間：加入充滿活力的團隊，參與核心產品開發，實現個人技術成長與價值。
5. 其他：免費飲料、咖啡、餅乾；員工聚餐；員工健康檢查。
1. Leave Policy: Annual Leave
2. Bonus and Welfare System: Year-End Bonus, Performance Bonuses, and Patent & Innovation Rewards
3. Professional Development and Learning Support
a. Subsidies for online or in-person courses and certification exam fees.
b. Regularly organized lectures, workshops, and book clubs.
c. Support for innovative projects with additional funding and resources.
4. Growth Opportunities
Join a dynamic team and contribute to core product development, fostering personal technical growth and value realization.
5. Additional Perks
a. Complimentary beverages, coffee, and snacks.
b. Team meals and gatherings.
c. Employee health check-ups.
