I am an empirical machine learning researcher with an interdisciplinary background spanning deep learning, generative models, LLM evaluation, and quantitative social science.

I have worked on computer vision and language-model systems, with hands-on experience in PyTorch pipelines, synthetic data generation, and model evaluation for medical imaging and robustness studies.

My research interests center on AI safety, model evaluation, adversarial robustness, and the societal effects of advanced AI systems. I enjoy turning open-ended research questions into reproducible experiments and clear, evidence-based conclusions.

I have co-authored peer-reviewed work on diffusion-based failure diagnosis and contributed to experimental studies that examine how linguistic variation affects AI-text detector reliability.

Alongside research, I have practical backend development experience using FastAPI, SQLAlchemy, and Node.js, and I am comfortable working across data analysis, experimentation, and software implementation.

I also have experience in teaching, mentoring, and organizing technical communities, which has strengthened my communication, leadership, and cross-functional collaboration skills.

I am open to opportunities where I can contribute to applied machine learning, evaluation, and research-driven product development in a rigorous and collaborative environment.