Projects

Co-founder & Backend Developer · letmecookonline.com

A deployed cooking web application. I designed and built the Express.js REST API: authentication with JWT, user profiles, dietary preferences, recipe-generation workflows, and image uploads backed by AWS S3. Also contributed to the Next.js frontend and collaborated through Git/GitHub.

• Express.js
• Node.js
• JWT
• AWS S3
• Next.js
• REST APIs

Autograd engine built from scratch

A scalar automatic-differentiation engine with dynamic computation graphs and reverse-mode backpropagation, implemented from first principles in Python. Covers the chain rule, gradient flow, and a small neural network library trained on top — no PyTorch, no shortcuts.

• Python
• Backpropagation
• Computation graphs
• Neural networks

Regression study with honest evaluation

A small regression study on the classic tips dataset, built around disciplined evaluation rather than model complexity. Every model is scored against a dummy baseline, compared under 5-fold cross-validation with leak-free preprocessing pipelines, and judged by paired fold-wise differences — which show that no richer feature set beats the single-predictor model once fold variance is accounted for.

• Python
• scikit-learn
• pandas
• Cross-validation
• Jupyter

Character-level language models, step by step

A series of character-level language models of increasing complexity: from bigram-count baselines to multilayer perceptrons with learned embeddings, built in Python and PyTorch. Focused on what actually happens inside a language model — loss surfaces, initialization, activation statistics — rather than calling a library.

• Python
• PyTorch
• Language models
• Embeddings
• MLPs

Full-stack accountability app in a production-style monorepo

An accountability and promise-tracking app built as a monorepo with a Next.js frontend and NestJS backend. Includes Dockerized local development with Compose, GitHub Actions CI/CD, and a PostgreSQL data layer — set up the way a real engineering team would ship it.

• Next.js
• NestJS
• PostgreSQL
• Docker
• GitHub Actions

Andrew Ng · DeepLearning.AI & Stanford — completed

Completed coursework covering supervised learning (linear and logistic regression, decision trees, ensembles), neural network training, and best practices for model evaluation and iteration. Taken alongside my from-scratch projects so the theory and the implementation reinforce each other.

• Supervised learning
• Model evaluation
• Neural networks

Andrej Karpathy's series — completed, implemented end to end

Worked through the Zero to Hero curriculum by building every artifact myself: the micrograd autograd engine and the makemore model series. Every lecture is paired with my own implementation and notes.

• Python
• PyTorch
• Deep learning