What I focus on.
I build systems and I probe them to understand how they break. My recent work sits at the intersection of security and machine learning, and I care most about rigor: following a question down to the detail that decides the answer.
Quantitative Research & Systems
Distributional forecasting, equity risk models, and production tooling for alpha workflows, built with testing and reliability in mind. Engineering that holds up under institutional standards.
Neural Network & Uncertainty Research
Generative models for financial time series and the uncertainty in their forecasts, with honest empirical evaluation. I treat unexpected and negative results as findings, not failures.
AI Security & RAG Safety
The area I am most interested in working in: prompt injection, red teaming, and control evaluations. Making retrieval pipelines resilient against the content they ingest, the top risk on the OWASP list for LLM applications.