AI Data Curation Intern, Vulcan
Taipeionsitejunior
via Greenhouse
About this role
實習目標
加入 Vulcan 團隊，與研究員及工程師並肩作戰！你將參與守護大型語言模型（LLM）安全的前線工作，深入探索 AI 漏洞檢測、數據隱私保護及模型防禦機制，累積最紮實的 AI 安全實務經驗。
核心職責
我們將複雜的技術開發轉化為具體的實習任務，讓你快速上手：
防護機制驗證數據生成 (DLP & Moderation)：
任務內容：設計用來測試「防禦牆」的輸入資料，模擬各類異常行為。
實作重點：撰寫測試案例，驗證藍隊的數據外洩防護（DLP）與內容審核（Moderation）機制是否能精準攔截個資外洩、暴力或歧視等不當言論。
數據標籤與分類 (Labeling)：
任務內容：擔任 AI 的「安全導師」，定義行為邊界。
實作重點：精準標註訓練與測試資料，識別「隱私洩漏」或「提示詞劫持（Prompt Injection）」等惡意指令，協助模型學習辨識風險。
測試結果分析與洞察：
任務內容：挖掘 AI 的潛在弱點，將數據轉化為情報。
實作重點：整理 Vulcan 平台的測試結果，分析模型在不同安全維度的表現，並協助團隊製作直觀的分析圖表與技術報告。
上班時間 09:00-18:00 (每月 3-5天，依工作量彈性安排)
Internship Goal
Join the Vulcan team and work alongside top-tier researchers and engineers to fortify the security of Large Language Models (LLMs).…
What we'd score you on
reqspace match rubricFive dimensions, recruiter-grade. Upload your resume and we'll generate a written explanation of where you fit and where the gaps are.
1
Skills match
We compare your skills against the role requirements.
2
Level fit
This role is junior-level. We check your trajectory against it.
3
Domain experience
Your work in the role's domain matters more than your years total. We weight recent and direct experience.
4
Recency
A skill you used last quarter weighs more than one from five years ago. We grade on recency, not lifetime.
5
Location fit
This role is based in Taipei. We weight your proximity and willingness to relocate.
Score yourself on this role.
Free · no card · written explanation included
More at Aift
- View →Chief Technology Officer/ Head of Engineering, Virtual insuranceTaipei, Taiwan
- View →Customer Care AssociateOneDegree Hong Kong Office
- View →Head of PartnershipOneDegree Hong Kong Office
- View →HR Specialist, VulcanTaipei, Taiwan
- View →iOS App developerTaiwan
- View →Business Development Manager/ Partnership Manager , CymetricsTaiwan