Research Software Engineer

Overview

Software engineer and undergraduate researcher at the AIEA Research Lab, building production autograding infrastructure for graduate- and undergraduate-level machine learning courses, and conducting research on improving LLM accuracy and interpretability.

Project: XAI Autograder

• Built production autograding infrastructure serving students across multiple machine learning CS courses
• Achieved 95% student preference rate for the new guidance system in a pilot study versus the previous autograding system
• Developed a tree-based code analysis system in Python to evaluate correctness, behavior, and logic of student implementations in ML chess assignments
• Integrated external Universal Chess Interface (UCI) engine APIs to benchmark student eval and minimax implementations for accuracy and performance
• Adapted autograder for undergraduate coursework, accelerating assignment iteration, deployment, and testing
• Performed large-scale debugging and analysis of untrusted student code; tightened security boundaries and sandboxing to prevent abuse and ensure system integrity
• Followed Agile/Scrum practices with weekly sprints, code reviews, and standups

Project: LLM Research

• Improved LLM accuracy and interpretability by 39% over baseline systems through symbolic logic and RAG integration
• Research inspired by: "Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning"