About Me Gmail , Linkedin, Github, Google Scholar                    

I am Dr. Dibyendu Brinto Bose, a Computer Science researcher working at the intersection of software engineering, machine learning, and software reliability. I recently completed my Ph.D. in Computer Science at Virginia Tech, where I was part of the Code World No Blanket research group under the supervision of Dr. Chris Brown. I will be joining Amazon in Seattle as an Applied Scientist, where I will continue working on machine learning and large-scale intelligent systems.

I have worked as an Applied Scientist Intern at Amazon and served as an Instructor of Record for CS 3114: Intermediate Data Structures and Algorithms at Virginia Tech. I received my Bachelor of Science in Computer Science and Engineering from the Bangladesh University of Engineering and Technology.

Exciting News:

• I will be joining Amazon as an Applied Scientist in Seattle. 

• I successfully defended my Ph.D. dissertation and completed my doctoral degree in Computer Science at Virginia Tech. 

• I worked in Amazon as an Applied Scientist Intern in summer 2025.

• I serve as an Instructor of Record for CS 3114, Intermediate Data Structures and Algorithms, at Virginia Tech. 

Research Interest: 

My research spans several interconnected areas:

• AR/VR Testing Methodologies: Metamorphic testing for AR applications, Object Scaling with Distance relations, Raycast within Boundary analysis, Visibility and Occlusion testing, and Nielsen's usability heuristics applied to mobile AR

• LLM-based Software Engineering: Multi-agent debate frameworks for Metamorphic Relations detection, stability-driven evaluation metrics, collaborative reasoning through structured deliberation, and ground truth correctness alignment

• Empirical Software Engineering: Security misconfigurations in Kubernetes manifests, graph-based dependency management analytics, deepWalk algorithm modifications for software library relationships, and developer experience analysis

• Computational Biology: Machine learning for DNA-binding protein prediction, Stacking Ensemble techniques, Recursive Feature Elimination with Cross-Validation (RFECV), and LLM-based approaches for antibiotic resistance gene classification