AI & Data Science Engineer — turning messy, real-world data into models people can trust and act on.
I turn messy, real-world problems into models that hold up under scrutiny — not just ones that score well in a notebook. That means owning the full lifecycle: cleaning inputs that rarely arrive clean, exploring what the data actually shows before assuming what it should show, engineering the features that matter, and defending every model choice with the evaluation metric the problem actually calls for.
I'm a B.Tech graduate in Artificial Intelligence and Data Science, increasingly drawn to deep learning and computer vision — the kind of work where you own a build from architecture choice through to a deployed, testable outcome, not just a plot.
That range has been shaped by project work in healthcare imaging, behavioral data, and public-facing AI applications, using Python, TensorFlow, PyTorch, OpenCV, Scikit-learn, Keras, SQL, and AWS fundamentals.
Exploratory data analysis of sleep-related data to uncover patterns and lifestyle factors that influence sleep quality.
View on GitHub →Analysis of historical oil price data to explore trends, volatility, and the factors driving price movement over time.
View on GitHub →Analysis of health and lifestyle data to identify patterns associated with common sleep disorders.
View on GitHub →An end-to-end model that predicts a mental health score from lifestyle and behavioral data — built, trained, and deployed as a working, testable product rather than a notebook-only exercise.
View on GitHub →A machine learning model trained on clinical and lifestyle features to predict heart disease risk.
View on GitHub →A machine learning system that predicts the likelihood of multiple diseases from patient health indicators, consolidating several diagnostic models into one workflow.
View on GitHub →