Code Intelligence/Software Analytics Intern

Job Type: Full-time Intern
Location: Beijing/Shanghai 

Group Introduction:
Join the AI-powered coding revolution! As part of Microsoft DKI team, we pioneer cutting-edge research and applications of multimodal large language models. We have led the development of impactful open-source projects including Wizard, TaskWeaver, and UFO. Collaborating closely with GitHub Copilot, VS Code, and Microsoft Copilot teams, we drive technological breakthroughs in code generation, program translation, test case synthesis, and reinforcement learning for coding, shaping the future of AI-assisted software development. 

Job Responsibilities (Choose between Engineering or Research): 

Engineering Intern: 

• Build code datasets for AI-powered code intelligence 
• Develop static/dynamic analysis tools 
• Implement real-time code analysis in GitHub Copilot workflows 
• Apply code analysis techniques to mission-critical distributed systems, improving reliability and security 

Research Intern: 

• Innovate in code-CoT prompting and programming instruction fine-tuning 
• Advance code representation learning with program synthesis techniques 
• Research AI-enhanced software analysis applications 
• Publish breakthroughs at PLDI/ICSE/FSE conferences 

Qualifications: 

• Strong programming skills in Python/Java/C++ with Linux experience 
• Experience in either: 

• • Software analysis tools (AST/CFG analysis) and distributed systems 

• • LLM frameworks (PyTorch/DeepSpeed) and prompt engineering 
• Understanding of compiler principles or code intelligence paradigms 
• Publications in software engineering/PL conferences preferred 
• Must be available for a full-time internship for 6 months or more. 

Internship Duration Requirements:
Must obtain permission from your academic advisor and commit to at least 6 months of internship. 

Please send your English or Chinese resume (in PDF/Word format) to: [email protected]. Please include “Code Intelligence/Software Analytics Intern” in the email subject line. 

 
岗位名称：代码智能/软件分析实习生
工作性质：全职实习生
工作地点：北京/上海 

团队介绍：
加入AI赋能编程的技术革新！微软DKI团队专注多模态大模型的前沿研究与应用，主导开发了Wizard、TaskWeaver、UFO等开源项目。我们与GitHub Copilot、VS Code、Microsoft Copilot等产品团队深度合作，在代码生成、程序翻译、测试用例合成、编程强化学习等领域持续创新，致力于打造下一代AI辅助开发范式。 

岗位职责（方向可选）： 

工程实习生： 

• 构建支持代码智能的大模型数据集 
• 开发动态/静态分析优化工具 
• 在GitHub Copilot中实现实时代码分析 
• 将代码分析技术应用于核心分布式系统，提升可靠性与安全性 

研究实习生： 

• 研发代码思维链提示与编程指令微调技术 
• 推进代码表征学习与程序合成方法 
• 探索AI增强的软件分析技术及应用 
• 在PLDI/ICSE等顶会发表创新成果 

岗位要求： 

• 扎实的Python/Java/C++能力，具备Linux开发经验 
• 满足以下任一领域经验： 

• • 软件分析工具（AST/控制流分析）与分布式系统 

• • 大模型框架（PyTorch/DeepSpeed）与Prompt工程 
• 理解编译原理或代码智能范式 
• 在软件工程/编程语言顶会有论文发表者优先 
• 每周全职工作5天，能够保证实习6个月以上 

实习时间要求：
需获得导师许可，并保证至少6个月的实习周期。 

请将完整的中/英文简历（PDF/Word形式）发送至：[email protected]。邮件标题中请注明“代码智能/软件分析实习生”。