PROJECTS

Architecture intelligence for large codebases. Combines AST parsing, graph analysis, and Recursive Language Models to detect anti-patterns, cycles, and layering violations. Multi-language support, tested on repos up to 3.4M LOC.

Code and materials from my ODSC APAC 2024 keynote. Practical implementations of knowledge distillation, pruning, quantization, and model parallelization for production LLM deployment.

Synthetic conversation dataset generator for training telecom customer service AI. Logic-based plan suggestions, multi-turn dialogues, and built-in dataset validation with quality metrics.

Fully connected feedforward neural network library with backpropagation, built from the ground up in vanilla Python. Configurable architecture, batch training, momentum, and regularization.