I am a young engineer with an appetite for building things that work in the real world. EireQuant is my flagship project and the place where I learn, test, and publish ideas in quantitative finance, macro economics and machine learning at my own pace. It is a long-running project that lets me explore methods and turn them into something that looks and behaves like a real investment stack.
I like hard problems, opportunities to grow and collaboration with like minded driven peers. Outside study and EireQuant I keep a simple routine that balances reading, training, and time with friends and family. I enjoy football, running, and travelling whenever I get the time. I read broadly across markets, engineering, and history, and I keep notes that often turn into ideas for the project. I work best when I own the outcome from idea to delivery and I love working with others, both in leadership and non leading roles.
My mathematical grounding is solid in advanced calculus, linear algebra, probability, and stochastic processes, with active practice through modelling work. On the engineering side I have shipped end to end pieces across data ingestion, feature building, and model training, and I have moved that work into live use through scheduling, testing, and careful monitoring. During my time studying Computer Engineering at university I have been given the opportunity to learn many engineering concepts such as control systems, signals and communications to name a few, I enjoy taking these ideas and applying them to areas unfamiliar to myself, knowledge should be malleable to the problems at hand. I have hands-on practice with classical machine learning and growing experience in deep learning with my final year project being an investigation into "Short Term Electricity Forecasting". I put real effort into evaluation, calibration, and clear reporting, when something fails I debug it methodically and I note what I learned.
Direct work with brokers and senior managers
I supported two projects that had to land cleanly. The first was test planning and execution for transition from the legacy system to the new modern frontend. The second was controlled movement of broker data to ensure all data was up to date. I built a set of Excel functions and checks that teams could run themselves which cut hand-offs and made sign-off faster.
From data to daily publication
I design and run a daily research stack that publishes model behaviour, equity curves, sector views, and calibration checks. The work spans data pipelines, strategy research, evaluation, and a public front end that explains the output clearly. This has been my first experience building a full-stack project so everyday has been a learning day.
Final year undergraduate
Project work in control systems, engineering entrepreneurship, and deep learning feeds directly into how I design and test the research stack. I am currently sitting on a 2:1 but will be aiming for a first come my graduation in 2026.
The project began as a personal attempt to bring finance and engineering together in a single place that I could own end to end. I wanted something close to a small research shop where I could decide the focus, build the tools, and carry the results through to publication. That structure lets me rotate between model design, data engineering, reporting, and product decisions which is a better way for me to learn and a better test of whether ideas hold up.
I am building the second Core model and tightening the production routines that support it. I am also planning weekly articles that would link current events to concrete parts of the system. The writing forces clarity and keeps me honest about what is working. Time is tight around final year study so any time dedicated to the project must be specific and focused.
Moving from static backtests to a live daily pipeline changed everything. Time zones, missing ticks, delayed files, and external services all fail at some point and the code has to handle that without drama. The other challenge is the simple fact that ideas are easy for me to outline yet actual implementation takes time. I often knew what I wanted the system to do before I had the skill to code it which meant I was limited most of the time by my coding ability. The answer has been steady practice, smaller steps, and better tests. As the system grows the hard part is choosing focus so that progress compounds rather than scattering effort.
I am drawn to fixed income trading where decisions are grounded in data and discipline. The mix of macro signals, micro structure, and risk control suits the way I think. I want to work with people who like to build rather than talk about building, who care about clean execution, and who are comfortable owning outcomes. This project matters to me and I would like to collaborate with like-minded driven individuals who hold a similar interest as myself.
The website is the front door. The model card shows performance and controls, the pipeline pages show the daily state of the system, and the compare page lets you judge risk and reward quickly. A whitepaper is on the way and will stitch the methods together so that readers can deep-dive into all theoretical parts of the backend design.