Background
CV
Education, experience, and skills.
Research Engineer with a PhD specialising in the robustness and evaluation of multimodal systems under degraded or missing inputs. Deep, first-principles understanding of machine learning fundamentals, from mathematical foundations to implementing custom architectures in PyTorch. Experience spans high-scale production environments at Amazon, maintaining 99.999% uptime, to research collaborations on beyond-5G networks and real-time motorway control systems. I combine academic rigour with low-level systems proficiency in Rust and Python to build reliable, high-performance ML pipelines.
Education
2021 — 2025
PhD in Computer Science
University College Dublin
Thesis: Learning to Associate — Handling Missing Modalities in Multimodal Systems. Developed lightweight reconstruction and stress-testing methods to analyse model behaviour under degraded, missing, or manipulated inputs. Researched post-training techniques to generate missing data, enhancing model robustness and adaptability in decentralised and federated environments.
2016 — 2021
B.Sc. in Computer Science
University College Dublin
First Class Honours. Dissertation: Analysing the Energy Consumption of Websites.
Experience
2026 — now
ML Engineer
Loop Design Lab · London
Multimodal ML for creative and design tools. Combining research rigour with production engineering to ship reliable ML systems.
2022 — 2024
ML Research Collaborator
Roughan & O'Donovan Engineering
Applied ML and statistical methods to predict traffic flow breakdowns, integrating results into live control systems on Ireland's busiest motorway. Investigated failure modes and representation stability in operational prediction models using real-time sensor data and network telemetry.
2021 — 2022
Applied ML Research Collaborator
InterDigital
Investigated the intersection of multimodal ML and beyond-5G networks, focusing on robustness issues caused by degraded inputs and distribution shifts in intelligent transport. Researched the transition of ML solutions from controlled environments to real-world, high-stakes network applications.
2019 — 2020
Software Engineer
Amazon
Contributed to large-scale observability systems processing billions of data points per AWS region per hour to ensure high reliability for AWS products. Integrated a statistical anomaly detection method into production for proactive identification of anomalous behaviour on devices. Optimised system performance through deferred execution methods and performance tuning in latency-sensitive distributed environments.
Technical Skills
- ML Fundamentals
- Backpropagation, attention mechanisms, and optimisation; model robustness, multimodal machine learning, federated learning, model calibration, and uncertainty analysis.
- Engineering
- Python, Rust, C, C++; performance engineering, SIMD optimisation, and building deterministic data pipelines.
- ML Tooling
- PyTorch, Candle, MLOps; multi-GPU training and HPC orchestration (SLURM).
Teaching & Awards
2021 — 2023
Teaching Excellence Award
Recognised for delivering lectures on algorithms and concurrent programming to 100+ students.
2021
John Kelly Memorial Award
Awarded for the highest academic performance in the graduating class.