AI Safety Researcher | PhD Student | Open Source Developer
I'm a Computer Science PhD student at Southern Illinois University researching AI safety, alignment, and adversarial robustness. I combine rigorous empirical methodology with theoretical foundations to build reliable ML systems. As a cancer survivor, I bring resilience and determination to complex challenges.
- AI Safety & Alignment - Scalable oversight, evaluation frameworks, adversarial robustness
- Mechanistic Interpretability - Understanding internal representations in neural networks
- Machine Learning Security - Adversarial attacks, defense mechanisms, reliable ML systems
- Statistical Methodology - Probabilistic models, reliability estimation, rigorous evaluation
- Cryptography - Encrypted search, privacy-preserving algorithms, secure computation
| Degree | Institution | Year | Notes |
|---|---|---|---|
| PhD Computer Science | SIU | 2024-Present | AI Safety & Alignment |
| MS Mathematics & Statistics | SIUE | 2023 | |
| MS Computer Science | SIUE | 2015 | Outstanding Graduate Student |
| BS Computer Science | SIUE | 2010 | Outstanding Junior |
Languages: Python, C/C++, R, Rust, TypeScript, Julia, LaTeX
AI/ML: PyTorch, HuggingFace, CUDA, scikit-learn, NumPy, Pandas
Systems: Linux, Docker, Git, PostgreSQL, Elasticsearch, Redis
- 2025 - Cognitive MRI of AI Conversations (Complex Networks)
- 2025 - Preventing Ransomware Damages using In-Operation Off-Site Backup (ICCI)
- 2023 - Reliability Estimation in Series Systems (Master's Project, SIUE)
- 2016 - Estimating Confidentiality of Encrypted Searches (IEEE CloudCom)
- 2015 - Encrypted Search: Enabling Standard IR Techniques (Master's Thesis)
