"程式設計接案" 相關案件

RD 工作

web 接案

1. 網站,後台管理系統,電腦應用程式,電腦遊戲,其他 2. 其他 3. 其他 4. 其他 5. 其他

描述： 1. We are building an offline-first AI Digital Doctor Platform — a real-time interactive avatar system that runs entirely on local hardware. This is not a chatbot project. This is not a website. This is a product-level AI system designed to operate without cloud dependency 2. We are building an offline-first AI Digital Doctor Platform — a real-time interactive avatar system that runs entirely on local hardware. This is not a chatbot project. This is not a website. This is a product-level AI system designed to operate without cloud dependency 3. We are building an offline-first AI Digital Doctor Platform — a real-time interactive avatar system that runs entirely on local hardware. This is not a chatbot project. This is not a website. This is a product-level AI system designed to operate without cloud dependency, with future SaaS scalability. Vision Create a single-node, fully offline AI system capable of: • Real-time doctor-avatar interaction • Low-latency speech-to-speech response • WebRTC-based video interface (Meet-like UX) • Modular LLM / STT / TTS architecture • Local knowledge ingestion & daily sync • Deployable on high-performance laptops or edge machines Phase 1 is a commercial MVP. Phase 2 expands into multi-clinic deployment and enterprise orchestration. ⸻ Technical Scope We are looking for engineers comfortable with: • Local LLM inference (7B–13B class models) • CUDA optimization & VRAM management • Quantization strategies • Streaming STT + TTS pipelines • WebRTC video + data channel integration • Audio-driven avatar rendering • Docker-based modular architecture • Offline RAG and versioned data ingestion This system must: • Run fully offline • Maintain ~1–2s response latency • Be modular and replaceable at each layer • Deliver full source code and deployment documentation ⸻ Who We Want Engineers who: • Have deployed local inference systems before • Understand performance bottlenecks • Can design scalable architecture from day one • Think in systems, not scripts This is an opportunity to build a foundational AI platform — not a contract task. All IP and derivative rights belong to 弛雅有限公司. ⸻ 4. We are building an offline-first AI Digital Doctor Platform — a real-time interactive avatar system that runs entirely on local hardware. This is not a chatbot project. This is not a website. This is a product-level AI system designed to operate without cloud dependency, with future SaaS scalability. Vision Create a single-node, fully offline AI system capable of: • Real-time doctor-avatar interaction • Low-latency speech-to-speech response • WebRTC-based video interface (Meet-like UX) • Modular LLM / STT / TTS architecture • Local knowledge ingestion & daily sync • Deployable on high-performance laptops or edge machines Phase 1 is a commercial MVP. Phase 2 expands into multi-clinic deployment and enterprise orchestration. ⸻ Technical Scope We are looking for engineers comfortable with: • Local LLM inference (7B–13B class models) • CUDA optimization & VRAM management • Quantization strategies • Streaming STT + TTS pipelines • WebRTC video + data channel integration • Audio-driven avatar rendering • Docker-based modular architecture • Offline RAG and versioned data ingestion This system must: • Run fully offline • Maintain ~1–2s response latency • Be modular and replaceable at each layer • Deliver full source code and deployment documentation ⸻ Who We Want Engineers who: • Have deployed local inference systems before • Understand performance bottlenecks • Can design scalable architecture from day one • Think in systems, not scripts This is an opportunity to build a foundational AI platform — not a contract task. All IP and derivative rights belong to 弛雅有限公司. ⸻ 5. We are building an offline-first AI Digital Doctor Platform — a real-time interactive avatar system that runs entirely on local hardware. This is not a chatbot project. This is not a website. This is a product-level AI system designed to operate without cloud dependency 6. We are building an offline-first AI Digital Doctor Platform — a real-time interactive avatar system that runs entirely on local hardware. This is not a chatbot project. This is not a website. This is a product-level AI system designed to operate without cloud dependency, with future SaaS scalability. Vision Create a single-node, fully offline AI system capable of: • Real-time doctor-avatar interaction • Low-latency speech-to-speech response • WebRTC-based video interface (Meet-like UX) • Modular LLM / STT / TTS architecture • Local knowledge ingestion & daily sync • Deployable on high-performance laptops or edge machines Phase 1 is a commercial MVP. Phase 2 expands into multi-clinic deployment and enterprise orchestration. ⸻ Technical Scope We are looking for engineers comfortable with: • Local LLM inference (7B–13B class models) • CUDA optimization & VRAM management • Quantization strategies • Streaming STT + TTS pipelines • WebRTC video + data channel integration • Audio-driven avatar rendering • Docker-based modular architecture • Offline RAG and versioned data ingestion This system must: • Run fully offline • Maintain ~1–2s response latency • Be modular and replaceable at each layer • Deliver full source code and deployment documentation ⸻ Who We Want Engineers who: • Have deployed local inference systems before • Understand performance bottlenecks • Can design scalable architecture from day one • Think in systems, not scripts This is an opportunity to build a foundational AI platform — not a contract task. All IP and derivative rights belong to 弛雅有限公司. 7. We are building an offline-first AI Digital Doctor Platform — a real-time interactive avatar system that runs entirely on local hardware. This is not a chatbot project. This is not a website. This is a product-level AI system designed to operate without cloud dependency, with future SaaS scalability. Vision Create a single-node, fully offline AI system capable of: • Real-time doctor-avatar interaction • Low-latency speech-to-speech response • WebRTC-based video interface (Meet-like UX) • Modular LLM / STT / TTS architecture • Local knowledge ingestion & daily sync • Deployable on high-performance laptops or edge machines Phase 1 is a commercial MVP. Phase 2 expands into multi-clinic deployment and enterprise orchestration. ⸻ Technical Scope We are looking for engineers comfortable with: • Local LLM inference (7B–13B class models) • CUDA optimization & VRAM management • Quantization strategies • Streaming STT + TTS pipelines • WebRTC video + data channel integration • Audio-driven avatar rendering • Docker-based modular architecture • Offline RAG and versioned data ingestion This system must: • Run fully offline • Maintain ~1–2s response latency • Be modular and replaceable at each layer • Deliver full source code and deployment documentation ⸻ Who We Want Engineers who: • Have deployed local inference systems before • Understand performance bottlenecks • Can design scalable architecture from day one • Think in systems, not scripts This is an opportunity to build a foundational AI platform — not a contract task. All IP and derivative rights belong to 弛雅有限公司.

軟體開發

段〇〇光

台北市中正區

顧客預算：十萬到五十萬

交件時限：急件: • AI 系統整合 • LLM 本地部署 • 語音辨識 STT • WebRTC 視訊工程 • GPU CUDA 優化 • Docker 部署工程師 • 全端工程師 AI 整合

2026/2/22

RD 工作

web 接案

1. 網站,後台管理系統,電腦應用程式,其他 2. 其他 3. 其他 4. 其他 5. 其他

描述： 1. • AI 系統整合 • LLM 本地部署 • 語音辨識 STT • WebRTC 視訊工程 • GPU CUDA 優化 • Docker 部署工程師 • 全端工程師 AI 整合 2. • AI 系統整合 • LLM 本地部署 • 語音辨識 STT • WebRTC 視訊工程 • GPU CUDA 優化 • Docker 部署工程師 • 全端工程師 AI 整合 3. • AI 系統整合 • LLM 本地部署 • 語音辨識 STT • WebRTC 視訊工程 • GPU CUDA 優化 • Docker 部署工程師 • 全端工程師 AI 整合 4. • AI 系統整合 • LLM 本地部署 • 語音辨識 STT • WebRTC 視訊工程 • GPU CUDA 優化 • Docker 部署工程師 • 全端工程師 AI 整合 5. • AI 系統整合 • LLM 本地部署 • 語音辨識 STT • WebRTC 視訊工程 • GPU CUDA 優化 • Docker 部署工程師 • 全端工程師 AI 整合 6. • AI 系統整合 • LLM 本地部署 • 語音辨識 STT • WebRTC 視訊工程 • GPU CUDA 優化 • Docker 部署工程師 • 全端工程師 AI 整合 7. • AI 系統整合 • LLM 本地部署 • 語音辨識 STT • WebRTC 視訊工程 • GPU CUDA 優化 • Docker 部署工程師 • 全端工程師 AI 整合 8. 本專案為本地離線 AI 醫師分身即時影音互動系統，需包含： 1. 本地 LL M 部署（不可依賴******** 2. 語音辨識 STT 與語音合成 TTS 串接 3. WebRTC 即時視訊架構（類 Google Meet 介面） 4. 2D 或簡易 3D 分身動畫整合（嘴型同步） 5. GPU CUDA 優化與效能調校 6. Docker 容器化部署與一鍵啟動 7. 開機自動執行 8. 醫師知識可每日更新並同步 9. 全部原始碼與部署文件完整交付 10. 著作權、修改權、擴充權歸屬弛雅有限公司 11. 不得使用侵權模型或未授權素材

APP設計

Ansxxx

台中市西屯區

客戶預算：五十萬以上

2026/2/22

app 接案

Programmer 工作

1. 指定完成日期 2. 兩套作業系統都需要 3. 商務程式 4. 不需要指定，聽從專家建議 5. 需要介面流程設計與程式建置

描述： 1. 2026/8/31

APP設計

鄭〇丸

苗栗縣竹南鎮

客戶預算：沒有預算概念

2026/2/21

app 接案

Programmer 工作

1. 無指定完成日期 2. 兩套作業系統都需要 3. 其他 4. 不需要指定，聽從專家建議 5. 需要介面流程設計與程式建置

描述： 1. 記錄 2. 記錄狗狗照片及相關資料，app可自動把逐天的資料變成統計圖表

APP設計

郭〇甫

屏東縣屏東市

客戶預算：五萬以下

2026/2/21

app 接案

Programmer 工作

1. 無指定完成日期 2. 兩套作業系統都需要 3. 遊戲 4. 不需要指定，聽從專家建議 5. 需要介面流程設計與程式建置

描述： 1. 簡單的遊戲功能

網頁設計

Bilxxx

彰化縣社頭鄉

客戶預算：三萬元以下

2026/2/21

網站接案

網頁接案

1. 任何時候 2. 規劃製作新網站 3. 需要介面流程設計與程式建置 4. 購物交易網站 5. 批發零售業

描述： 1. 都不用純貿易公司產品展示

軟體開發

段〇〇光

台北市中正區

顧客預算：五十到一百萬

交件時限：指定交件期限: 第一階段母體系統開發期限為 6–8 週，需分階段驗收（架構設計完成 → 核心功能完成 → 可上線版本完成）。

2026/2/20

RD 工作

web 接案

1. 網站,後台管理系統 2. 不清楚，聽從專家的建議 3. 有想法、介面流程設計與測試版 4. 部署,維護,技術支援 5. 有

描述： 1. 本案為平台型系統母體架構開發（非套版），需具備後端架構設計經驗。核心包含：RBAC 權限模型、多角色架構、分潤機制、API Layer 設計與模組化擴充能力。第一階段需完成可上線母體系統，並完整交付原始碼（前端、後端與資料庫）、ERD、API 文件與部署文件。採分段里程碑付款，智慧財產權及著作權需移轉至甲方，不得技術鎖定。 2. 第一階段母體系統開發期限為 6–8 週，需分階段驗收（架構設計完成 → 核心功能完成 → 可上線版本完成）。 3. 本案為平台型母體架構開發，非形象網站或套版商城。需具備後端架構設計能力，能清楚說明 RBAC 權限模型、多角色資料模型、分潤機制資料庫設計與 API Layer 架構設計思路。重視可擴充性與模組化架構，需避免技術鎖定，並可完整交付原始碼（前端／後端／資料庫）、ERD、API 文件與部署文件。僅接受具實際平台開發經驗者提案。