About Me

I’m Josh — a quantitative researcher and data scientist working at the intersection of financial markets, optimization, machine learning, and AI.

My work focuses on turning messy real-world problems into quantitative systems: building optimization frameworks, designing machine learning pipelines, working with alternative and market data, and developing tools that help translate models into actual decisions.

I’m particularly interested in:

• Optimization & Operations Research — portfolio construction, allocation, constrained optimization, and decision systems
• Machine Learning — statistical learning, anomaly detection, representation learning, and deep learning
• Financial Markets — securities finance, market structure, portfolio analytics, and quantitative research
• AI Engineering — agents, evaluation frameworks, retrieval systems, and production AI workflows
• Data & Infrastructure — scalable research pipelines, feature engineering, APIs, and analytical tooling

Background

My path into computer science has been somewhat unconventional.

I originally studied economics and econometrics, which led me into quantitative finance and investment research. Over time, increasingly technical problems pushed me deeper into programming, optimization, machine learning, and software engineering.

I’m also a CFA charterholder and am completing a Master’s in Computer Science at Georgia Tech, specializing in Machine Learning.

That combination shapes how I approach technical problems: I care about the mathematics, but I care just as much about whether a model survives contact with the real world.

What You’ll Find Here

This site is my public notebook for things I’m learning, researching, and building.

Expect notes and projects covering topics such as:

• Deep learning and machine learning
• Quantitative finance
• Optimization
• Algorithms and computer science
• AI agents and evaluation
• Market research
• Research papers and experiments
• Tools I’ve built because I couldn’t find exactly what I wanted

Some posts will be polished. Others will be closer to working research notes.

The goal is simple: learn in public, build useful things, and document the reasoning along the way.

Current Interests

Right now, I’m especially interested in the overlap between:

\[\text{Markets} + \text{Optimization} + \text{Machine Learning} + \text{AI}\]

I think some of the most interesting problems aren’t purely predictive.

They’re about using models to answer a harder question:

Given what we know right now, what should we actually do?

That’s the territory I like working in.