Background & Philosophy

I am currently pursuing an MSE in Financial Mathematics at Johns Hopkins University, where my coursework and research focus on stochastic processes, machine learning in finance, derivatives, time series, and systematic trading. My practical experience spans end-to-end trading system development, from data engineering and signal design to portfolio construction, backtesting, monitoring, and communication of results to both technical and non-technical stakeholders.

At SNTIMNT.AI, I have worked on crypto trading research and system design with CTO-level ownership, managing a five-person quant team and helping build a full research-to-execution pipeline. My work there includes reinforcement learning-based strategy development, sentiment integration from news and social media, performance dashboard design, and translating system capabilities into diligence-ready narratives for fundraising.

In parallel, my academic and research work includes systematic arbitrage, factor structure analysis, high-frequency feature engineering, and behavioral-finance-driven bubble detection. I am especially interested in building trading systems that are not only predictive, but also interpretable, robust, and useful under real market constraints.