Having worked in the EdTech sector for over five years, I have gained a deep appreciation of the value that AI and data-centric technologies confer to their users. Fascinated to learn how these technologies work, and how they can be delivered in production, I have developed skills in Python, R, SQL, data science methodologies, statistics, mathematics, machine learning, and DevOps and Cloud platforms.

• Languages: Python, R, SQL
• Databases: PostgreSQL
• Cloud Computing: Azure
• Tools & Platforms: Git, GitHub, Bash, Docker, Kubernetes, Terraform
• Mathematics: Multivariate Calculus, Linear Algebra
• Statistics: Hypothesis testing, Distributions, Bootstrapping

• Azure DevOps Pipeline: In this project I containerise a pre-built python application; provision the infrastructure needed to run the application through an aks cluster; implement a rolling update strategy in the Kubernetes deployment; and design and implement an Azure DevOps build & release pipeline to automate application deployment to AKS.
• Titanic Kaggle Competition: This project encompasses the data exploration/preparation, and model development/evaluation I undertook to submit predictions as part of the kaggle Titanic Competition
• DIY Linear Regression: Here I developed my own Linear Regression models from scratch, and benchmarked them against scikit-learn. The best performing model uses Gradient Descent with Momentum, and has achieves accuracy scores similar to scikit-learn for a wide range of hyperparameters - and does so in a manageable timeframe
• DIY K Means Clustering: Here I developed my own K Means Clustering model from scratch. My model achieves almost the same mean squared error as the scikit learn model.
• Einstein's Riddle: In this Project, I find a solution to Einstein's Riddle using Python