Open to ML / Applied AI Engineering roles

Building end-to-end
AI systems for
real-world problems.

// ML Engineer · AI Security Research

3rd-year Artificial Intelligence & Computer Science undergraduate at the University of Edinburgh, building ML systems that work on real data and solve real problems.

I specialise in converting complex, real-world data streams into clean, structured data through the development of modular pipelines.

My work ranges from video-analysis systems for judo to anonymisation tools for email corpora.

I recently completed an AI & Cybersecurity research internship at the University of Edinburgh's School of Informatics.

View my work Get in touch

2 public projects · AI security research experience · University of Edinburgh

01 / about

Turning research into real systems

Hi, I'm Conor!

I enjoy turning messy, unstructured data into reliable inputs for machine-learning systems, building practical pipelines around them, and communicating technical ideas clearly.

Outside university, I train in Judo, which inspired my latest project: an AI-assisted coach for post-match analysis. It currently takes raw match footage and automatically identifies and clips attempted throws. The next stage is developing a model that can provide coaching insights by analysing why each attempt succeeded or failed.

Toolbox

languages

Python Java JavaScript C MIPS assembly

ml / ai

PyTorch Ultralytics YOLO v11 LSTM / RNNs LLM evaluation NER evaluation

security & data

Data preprocessing Anonymisation

tooling

Vercel Kaggle Git

02 / research experience

AI & Cybersecurity Research Internship

Recently completed a research internship at the University of Edinburgh’s School of Informatics.

Research Internship · Completed

Research Contributions

Contributed to two projects during an AI & Cybersecurity research internship.

Designed and implemented an automated system for anonymising email corpora.
Sourced and curated a research dataset, building a labelling interface that made annotation approximately 4× faster.

Source code for the anonymisation system is currently private.

Role: Research Intern Institution: University of Edinburgh

03 / projects

Selected work

End-to-end builds, from model research to deployed applications and teaching resources.

Judo Clipper

PyTorchPythonUltralytics YOLO v11AWS S3FastAPIModalVercel

An AI-powered video-analysis system that uses YOLO pose-estimation outputs as input to a custom LSTM model, automatically identifying and extracting throw-attempt clips from full judo matches.

Visit website

System repo Research repo Write-up

EdinburghAI Workshops

PythonPyTorchKaggle

Self-authored resources for AI-focused workshops delivered to students at the University of Edinburgh's student-led AI Society.

concepts taught

YOLO Pose DetectionData PreprocessingLSTMRecurrent Neural Networks

Resources repo

Society contributions Write-up

04 / contact

Let's build something.

I'm actively looking for ML / Applied AI Engineering opportunities and open to research collaborations. Feel free to reach out.