Building the Full Stack foundations for Intelligent Software.

I'm Jai Parakh, a backend engineer who builds AI-driven systems end to end, from scraping raw data to deploying models at scale. I've spent four years shipping production systems across healthcare, fintech, and AI marketing.

I am currently completing an MSc in AI & ML at the University of Limerick, with research internship at BDS Group (Lero) focused on anomaly detection for wind turbines, specifically whether autoencoder-based models can generalise across turbines rather than requiring one model per turbine.

Most recently I built CocktailAI, a genetic algorithm that generates personalised cocktail recipes using custom-trained taste classifiers deployed on AWS. It's the kind of project that sits at the intersection of ML, systems design, and cloud architecture, which is exactly where I like to work.

I care about systems that actually run in production and handle failures gracefully, cost what they should, and don't need babysitting. Outside engineering I recharge through photography, swimming, and archery, which turns out to be good training for the patience required in model debugging.