An aspiring Machine Learning and Data Scientist, I am currently studying an Advanced Computer Science: Artificial Intelligence MSc at The University of Manchester and then a looking for a graduate job in Manchester or London at small Startup or fast-moving companies.
I aspire to work on complicated problems, where I can develop my innovative, user-oriented problem-solving skills to help create smart solutions.
May 2020 - July 2020
I worked in the Materials Innovation Factory (MIF), a world-leading research facility, with Unilever on their dedicated floor in the building, in the team responsible for automation and standardisation of the laboratory robots, equipment and data pipelines. Through the Unilever’s in house data entry systems, I worked processing the data that the laboratory equipment produces. Developing my Python skills as I wrote scripts to process outputs from the robots used across MIF, to simplify the regular generation of visualisations that provide at a glance, up to date details of critical metrics. Through communication with colleagues with a chemistry background, to understand what goes into making Unilever products, I was able to extract the questions that they would like visualisations of the data to help them answer. I worked with Power BI to develop a variety of models and visualisation of Unilever and Competitor products to provide insight into the direction for further research and development.
November 2019 - May 2020
Responsible for working with managing updates and replacements of next-generation technologies on computers running essential laboratory and automation equipment throughout the Materials Innovation Factory (MIF). Worked with colleagues across the MIF to make sure vital data was not lost and that downtime, while improvements were made, was limited to the bare minimum.
June 2014 - August 2019
I spent my summer studying Deep Learning with the guidance of my research project supervisor. I built, tested and trained Machine Learning models, gaining an understanding of Deep Learning, Neural Networks theory and fluency in Python. My research was focused on Graph Neural Networks, a novel form of Artificial Intelligence that focuses on developing and understanding algorithms that will work with Non-Euclidian data such as social networks, sensor networks and point clouds. I implemented cutting edge models by reviewing leading current academic research on GNNs required to work with Non-Euclidian data. I gained familiarity with Pandas and other python data science packages, as well as a deep understanding of PyTorch as I worked to understand the implementation of the PyTorch Geometric extension library. I continued this project in my final year of university, working specifically point clouds that have the potential to provide improved performance over current standard Euclidian data-based computer vison. I have also built a working knowledge Linux systems using bash and Slurm Workload Manager on the universities High-Performance Computing cluster.
2020 - 2021
The University of Manchester
With either Excel or Python with Pandas and Seaborn I am able to quickly clean and extract relevant section of data to compose complex visualisations. Proficient in feeding this pre-proccessed data to various analytic solutions to extract actionable insights.
Developing a strong understanding of the problems organisations face with data life cycle management. Capable of efficiently modelling using a variety of different core data models — SQL, semi-structured and graph — challenging domain data.
2017 - 2020
The University of Liverpool
Improved computer vision performance on point cloud datasets by developing novel Graph Neural Network (GNN) models.
I used the High-Performance Computing facilities of the university via, Remote SSH to the Linux terminal; I ran scripts to train and test ML models on Alces Flight and Slurm Workload Manager.