Juan Zhai is an Assistant Professor in the Manning College of Information & Computer Sciences (CICS) at University of Massachusetts, Amherst (UMass). She co-directs the Laboratory for Advanced Software Engineering Research (LASER) lab. She is also a member of UMass NLP group. She works on trustworthy computing systems, with a focus on ensuring the correctness, reliability, and security of modern software and machine learning systems, including emerging agentic AI systems.
I am always looking for students to work with. Drop me an email if you are interested in working with me!
Trustworthy AI for Software and ML Systems
I build trustworthy computing systems, with a focus on ensuring the correctness, safety, and reliability of modern machine learning and software systems, including emerging agentic AI systems.
My research draws on foundations from software engineering, security, and systems, and develops methods for testing, formal specification, and runtime assurance to make complex systems auditable and dependable in real-world environments. I am particularly interested in agentic AI, where autonomous systems execute multi-step workflows and interact with external tools, creating new challenges for verification, security, and control.
Formal Methods and Verification
A core focus is improving software correctness through formal specifications and verification-oriented techniques. I work on methods to derive precise behavioral specifications from natural language and code artifacts, enabling stronger testing, analysis, and reasoning about system behavior.
I am also interested in how formal reasoning can be integrated with AI-based development workflows so that intelligent code generation is grounded in explicit correctness constraints.
Reliability and Robustness of AI Systems
I develop practical techniques to test, diagnose, and improve the reliability of AI software stacks, including deep learning frameworks, model training pipelines, and deployment workflows. The emphasis is on identifying failures early and reducing costly downstream errors.
This includes work on robustness testing, automated debugging and repair, and system-level quality assurance for machine learning tools and models.
Responsible and Accountable AI Systems
Another key direction is improving fairness and accountability in AI systems. I investigate how bias emerges across the machine learning lifecycle and develop approaches to detect, explain, and mitigate those issues.
I also study software documentation and communication artifacts, such as comments and natural language specifications, to better align implementation behavior with intended requirements and strengthen trustworthy AI development workflows.
Current Students
PhD Students (Advisor)
Gehao Zhang
2nd year PhD student
Yi Su
Starting Sep. 2026
PhD Students (Committee Member)
Juan Altmayer Pizzorno
5th year PhD student
Zhanna Kaufman
5th year PhD student
Master's Students
Xiaofan Lu
1st year master's student
Undergraduate Students
Justin Chen
Senior undergraduate student
Sheyan Yu
Senior undergraduate student
Join Our Research Group
For Prospective PhD Students
I am actively seeking motivated PhD students interested in Software Engineering, AI Safety, and Trustworthy AI research. Strong background in programming and interest in research is essential.
Application: Apply through the UMass CS PhD program and mention my name in your application.
For Undergraduate and Master's Students
I welcome motivated undergraduate and Master's students to join our research activities. Research experience provides valuable skills and insights for your academic and professional development.
Opportunities: Independent study courses, research assistant positions, and co-authorship on publications.
📧 Contact: Please email me with your CV, transcript, and research interests.
Loading publications...
Graduate Level Courses
Hot Topics in Software Engineering Research
Fall 2024Theory and Practice of Software Engineering
Fall 2025, Fall 2024, Spring 2024Undergraduate Level Courses
Software Engineering
Spring 2023, Spring 2020Data Structure
Multiple SemestersIntroduction to Computer Science
Multiple SemestersComplete Teaching Timeline
Note: ×2 indicates I taught two separate sections of the course that term