I build and maintain data systems in Python and SQL as a Data Engineer at Bitwise, and spend my time outside of work on the theoretical foundations of Artificial Intelligence and Machine Learning.
What draws me in is the mathematics underneath the models — Linear Algebra, Optimization, and Statistical Learning Theory. I'm particularly interested in why learning algorithms behave the way they do: their convergence properties, their generalization behavior, and what can be said about them from first principles rather than from empirical results alone.
My working method is to close the loop between the two: take an abstract result, implement it, and see whether the experiment agrees with the theory. I'd rather understand one algorithm to the bottom than five at the surface — depth over familiarity, with an emphasis on algorithmic reasoning and analytical clarity.
Long term, I want to contribute to AI/ML research and development, building systems grounded in solid mathematical theory and principled design.
| Area | What I'm working through |
|---|---|
| 📐 Linear Algebra | Matrix decompositions, spectral methods, geometry of high-dimensional spaces |
| 📉 Optimization | Convexity, gradient methods, convergence rates and their proofs |
| 📊 Statistical Learning Theory | Bias–variance, VC dimension, generalization bounds, regularization |
| 🛠️ Engineering | Reproducible experiments, data pipelines, clean numerical implementations |
- 🔭 Currently working on data engineering at Bitwise
- 🌱 Currently learning optimization theory and the statistical foundations of learning
- 💬 Ask me about Python, SQL, data pipelines, and the math behind ML
- ⚡ I believe an algorithm you can't derive is an algorithm you don't yet know
Languages
Machine Learning & Deep Learning
Scientific Computing & Statistics
Data Engineering
Databases
Cloud & Platforms
Tools
