I am a PhD Computer Science student at the University of Central Florida focused on AI research across Computer Vision, Natural Language Processing, and large language model evaluation.

My current research centers on social reasoning and mental-state modeling in LLMs. I am developing stronger evaluation workflows for belief tracking, narrative consistency, and benchmark reliability. While this work is still under active development, it has helped me build practical skills in structured evaluation design, annotation operations, schema-driven analysis, and large-scale model auditing.

Across projects, I work from idea to delivery: framing research questions, building technical pipelines, coordinating teams, running experiments, and communicating results through papers, demos, and presentations.

Research and Engineering Focus

• Social reasoning and Theory of Mind evaluation in LLMs.
• Benchmark construction with reproducible protocols and quality controls.
• Multimodal AI workflows spanning text, vision, and behavioral signal analysis.
• Applied ML system development across local compute, cloud APIs, and full-stack infrastructure.

What I Bring

• Strong project leadership across research and engineering teams.
• Experience turning ambiguous ideas into deployable systems and measurable outcomes.
• A balance of technical depth, execution discipline, and clear communication.

I am currently seeking AI Research and Machine Learning internship opportunities.