Microsoft Research Intern - Systems Reliable Scalable AI Agents 

Taiwan, Taoyuan City 

160713238

Recent breakthroughs in generative AI have opened the door to powerful agents—but making them truly dependable and scalable requires solving deep ML and systems problems. That’s where you come in.

🔍 What You’ll Work On

As part of our team, you’ll explore and innovate across a range of topics, including:

• ✅ Formal Verification : Modeling and verifying AI agent's behavior to ensure correctness.
• ⚙️ Reliability & Safety : Ensuring agents execute tasks without failure or unintended side effects.
• 🧠 Intelligent Task Handling : Designing agents that can efficiently manage complex workflows.
• 🔐 Secure Execution : Guaranteeing agents operate in isolation and only perform authorized tasks.
• 💡 Efficiency Optimization : Minimizing the number of steps, step latency, and costly interactions with LLM backends.
• 🛠️ Tooling for Developers : Building frameworks that accelerate agent development.

🌟 Why This Internship?

• Collaborate with world-class researchers and engineers at Microsoft Research .
• Work alongside product teams to bring your ideas to life.
• Tackle real-world problems with the potential for massive impact.
• Publish your work in top-tier conferences.

This is more than an internship—it’s a chance to shape the future of AI systems.

Required Qualifications

• Currently enrolled in a PhD program in Computer Science or a related STEM field.

Other Requirements

• Research Interns are expected to be physically located in their manager’s Microsoft worksite location for the duration of their internship.
• In addition to the qualifications below, you’ll need to submit a minimum of two reference letters for this position as well as a cover letter and any relevant work or research samples. After you submit your application, a request for letters may be sent to your list of references on your behalf. Note that reference letters cannot be requested until after you have submitted your application, and furthermore, that they might not be automatically requested for all candidates. You may wish to alert your letter writers in advance, so they will be ready to submit your letter.

Preferred Qualifications

• Experience of building scalable and reliable AI systems.
• Demonstrated ability to develop original research agenda.
• Ability to collaborate effectively with other researchers and product development teams.
• Proficient interpersonal skills, cross-group, and cross-culture collaboration.
• Ability to think unconventionally to derive creative and innovative solutions.