David OBrien

Current Computer Science PhD Candidate at Iowa State University under the advisement of Dr. Hridesh Rajan. My research activities and internships at Apple and Collins Aerospace have exposed me to a wide range of applied machine learning techniques such as training large language models, convolutional neural networks, and reinforcement learning-enabled robotic systems. I have competitively published at top-tier software engineering conferences at the intersection of software maintenance and machine learning (ESEC/FSE’22 and ICSE’24) and providing data-driven observations to motivate programming language evolution (ICSE’24).

Publications

David OBrien, Sumon Biswas, Sayem Imtiaz, Rabe Abdalkareem, Emad Shihab, Hridesh Rajan. Are Prompt Engineering and TODO Comments Friends or Foes? An Evaluation on GitHub Copilot. In 46th International Conference on Software Engineering (ICSE), 2024.
David OBrien, Robert Dyer, Tien Nguyen, Hridesh Rajan. Data-Driven Evidence-Based Syntactic Sugar Design. In 46th International Conference on Software Engineering (ICSE), 2024.
David OBrien, Sumon Biswas, Sayem Imtiaz, Rabe Abdalkareem, Emad Shihab, Hridesh Rajan. 23 Shades of Self-Admitted Technical Debt: An Empirical Study on Machine Learning Software. In 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE), 2022.

Previous Experiences

Laboratory for Software Design (Summer 2020 - Present)
- Advocate for and performed self-admitted technical debt research. Evaluated technical debt repayment using large language models on over 1000 instances leveraging various prompt engineering techniques to characterize future improvements to state-of-the-art large language models (ICSE’24). Explored and recommended best practices to ML developers to improve upon ML software maintainability (ESEC/FSE’22).
- Implement new functionality to the Boa Language and Infrastructure, including the implementation of scalable frequent subgraph mining algorithms with Hadoop's MapReduce framework. Contributions enable researchers to mine subgraphs from large-scale datasets (over 150 million graphs).
- Fine-tuned multiple state-of-the-art large language models (CodeT5, CodeReviewer, NatGen) upon a dataset I created of 400K data points from 8000 open-source repositories to automatically identify multiple refactoring opportunities in source code with 60% exact match accuracy.
Apple - ML Engineer Intern (Summer 2023)
- Implemented a regression testing computer vision framework to analyze multi-versioned UI screenshots and quantify their differences. Evaluations shows our technique of deep-learning-enabled difference identification is 20x faster and 55% more correct than manual evaluation.
- Experimented with multiple pre-trained architectures and fine-tuned convolutional neural networks to determine best solution for business problem.
- Manually curated a dataset of multiple screenshots representing regression-inducing changes and non-regression-inducing changes.
Collins Aerospace - AI Engineer Intern (Summer 2022)
- Maintain multi-year text-extracting software originally valued at 9.8 million dollars. Contributions include identifying and resolving defects, removing obsolete code, and leading discussions on worthwhile coding standards to adopt to reduce developer maintenance waste and promote easily maintained software.
- Apply supervised learning processing techniques on unseen data to provide clients with organized data from AWS.
- Experimented with reinforcement learning to guide a simulated car through a course which consistently exceeded score expectations to motivate autonomous systems research.
- Cleaning, organizing, and evaluating a dataset consisting of multiple real-time sensors used by future engineers.

David OBrien

Research Interests

Software Engineering

Machine Learning

Program Analysis

Big Data Mining

Publications

Previous Experiences

Laboratory for Software Design (Summer 2020 - Present)

Apple - ML Engineer Intern (Summer 2023)

Collins Aerospace - AI Engineer Intern (Summer 2022)