Data & AI Projects
A curated collection of my work in machine learning, generative AI, and data engineering.
GenAI Projects
Retrieval-Augmented Generation (RAG) based assistants and Agentic workflows.
Headwater
An advisory data platform that automates schema discovery, profiling, and documentation, generating SQL models and quality contracts for human review.
Luminary
A local-first active learning cockpit that combines a document reader, cited Q&A (RAG), AI-generated flashcards scheduled using the FSRS algorithm, and markdown notes.
Fly-O-Myte
The smart travel expense optimizer for Australian families. Tracks trips, builds price history, and gives clear booking advice.
Doc-Mate
Intelligent document assistant powered by GenAI and RAG.
Content Pal
Streaming media content assistant using RAG for hybrid search and recommendations.
ML & Data Engineering
Machine learning models and data engineering toolkits.
dkit
A data engineer's toolkit for schema inference, data profiling, SQL execution, validation, and pipeline scaffolding.
Chase Prediction
Prediction model to determine the chances of winning an IPL chase based on match data.
PyFlink Score Publisher
Real-time T20 match score publisher for Chase Prediction, using Apache PyFlink.
Flink Score Publisher
Real-time T20 match score publisher for Chase Prediction, using Apache Flink (Java).
Movie Rating Prediction
Machine learning model to predict movie ratings based on reviews and genre.