CakeResume Talent Search

lines Lua. Client Unity, DOTS, ECS, .NET. Server Socket, Boost, Asio, ECS, EnTT, FlatBuffers, Protobuf, Linux, MySQL, .NET. DevOps Jenkins, GitLab CI/CD, Travis-CI, Docker, GCP, Debian, SonarQube. Misc. Data-Oriented Design, FP, OOP, IoC, DI, Optimization, Benchmarking, Testing, MSVC , GCC, LLVM, Clang, CMake, Redmine, Trello, Slack. Experience 資深工程師 中華網龍 •present 導入 CI、unit tests、code review、linter 及其他分析工具，自動化流程，減少 90% 以上非遊戲邏輯方面

IP-cam and sport cam. 7.5 years involved in multimedia functionality development 1 year in developing X86 firmware & EFI BIOS program. Experience Experience : NovemberNow: senior engineer of SAMBA TV 1. Contribute to C++ standard library to promote inplace merge algorithm: for GCC , for LLVM , report . 2. Publish patent of improve adaptive streaming quality; patent . 3. Publish patent of share file between mobile devices; patent . 4. Publish patent of smart rate allocation for multiple sessions on browser; patent . Experience : AprilNovember: technical leader of Noovo tech 1.

案，支援RPA 功能與各系統串接。 維運管理:負責 UMC 12X 聯芯 RPA 平台 系統維運與需求評估。 新技術導入:影像辨識相關新技術導入、 LLM 客製化 AI Agent 串接 緯創軟體開發工程師 ， NovJul.2022 提供客戶端聯華電子軟體開發服務，主要負責 RPA 流程機器人於各製程機

models for precise text intent classification and NER Services. I architectured an API server, leveraging Tornado and Redis. deployment with GitLab-CI . At the same time, I integrated ELK for seamless data aggregation and system enhancement, ensuring a robust data lifecycle for training language models. OTHERS LLM Research, 2023 – now, Side Project I contributed to a side project where we developed an elementary school science debate robot using advanced language models and techniques.This robot simulates opposing viewpoints and provides users with adjustment suggestions at the end of the debate. We delved into technologies

tune LLMs, Text Generation, Multi-Document Summarization, Recommendation System, Text Classification, Named Entity Recognition, CoT Research and Work Experience Research Assistant OctPresent Institute of Information Science, Academia Sinica, Taiwan Natural Language and Knowledge Processing Lab (NLP Lab) National Taiwan University Hospital (NTUH): Focused on exploring the generality and expertise of LLMs ( e.g., LLaMA2, Zephyr. ) in medical Q&A applications, improving model performance by 2.01% . Efficiency Optimization: Utilized Low-Rank Adaptation (LoRA) for training LLM, reducing parameter training volume to 2% , decreasing memory usage by 70%, and increasing training speed by 25%. Architecture

50%提高到90%，並擴展了測試範圍，從單一路徑擴展到多個路徑。 開發並實行AI資料抓取系統模型，用於整合各部門資料，使用LLM上的prompt和embedding方法來查詢信息，以減少非研發部門的編碼工作。 通過優化自動測試系統，成功降低了檢測模型的錯誤率50

automation tools to swiftly adapt models to new data. Developed an API service used as an internal tool within the company, leveraging OpenAI Whisper for automatic speech recognition and ChatGPT for intelligent language translation, resulting in approximately an 80% reduction in manpower and time costs. Fine-tuned a Llama-based Large Language Model (LLM) and, by integrating Langchain and Pinecone, optimized the search experience on our website. AprJulMachine Learning Researcher, Lab. for Cloud Dynamics and Modeling, National Taiwan University, Taipei, Taiwan Developed a model using U-net to detect ship tracks in satellite images, resulting in