Professional Experience

Conducting research under Dr. Long Cheng on whether societies of Large Language Model agents can realistically simulate human behavior and support early-stage behavioral studies.

Research & Contributions

• Researching whether societies of LLM agents can substitute for human participants in behavioral pilot studies.
• Reproducing published behavioral experiments and designing new studies with AgentSociety, YuLan-OneSim, Generative Agents, and related multi-agent frameworks.
• Developing a taxonomy and metrics for behavioral realism, consistency, and human alignment across decision-making and social scenarios.
• Designing and reproducing behavioral experiments such as Trust Games and Dictator Games to compare LLM-agent decisions against established human behavioral data.
• Exploring evaluation methods and benchmarks for quantifying behavioral realism, consistency, and human-agent similarity.
• Building toward a research survey on the strengths and limitations of LLM agents for simulating human behavior, including their potential role in early-stage studies.

• Designed Jupyter labs and assignments covering data preprocessing, supervised learning, unsupervised learning, model evaluation, and visualization
• Built automated grading pipelines with Python and nbgrader to improve scoring consistency and reduce manual effort
• Maintained live course infrastructure and resolved notebook and autograder issues
• Explained machine-learning concepts and debugged student code during office hours
• Collaborated with faculty on curriculum design and course deployment on Coursera
• Debugged and resolved autograder and grading pipeline issues via Salesforce tickets, implementing fixes, validating outputs, and deploying updated notebook versions

• Performed end-to-end, regression, and integration testing for enterprise telecom systems supporting AT&T
• Designed test cases and validation strategies for new feature releases based on product requirements and stakeholder discussions
• Ran functional, UI, and API release tests with Selenium and Postman
• Collaborated with cross-functional global teams (US & India) in Agile environments to ensure smooth release cycles
• Participated in feature planning, requirement analysis, and system validation across multiple production releases