Nicholas Gray

Experience

Postdoctoral Research Associate — Medical AI

University of Liverpool, Liverpool, UK

⟶

Details
  • Built and evaluated machine-learning models to support real-world decision making, with a focus on calibration, uncertainty estimation, and robustness in high-risk environments.
  • Developed reproducible data processing and modelling pipelines for heterogeneous medical datasets, supporting validation, iteration, and future deployment.
  • Worked closely with clinicians and non-technical stakeholders to translate model performance and uncertainty into actionable risk information.

Research Data Scientist (Secondment)

Safehinge Primera, Glasgow, UK

⟶

Details
  • Designed data pipelines to extract behavioural signals from radar time-series data, enabling scalable pattern recognition and risk flagging.
  • Developed and evaluated machine-learning models for anomaly detection in real-world environments, balancing sensitivity and false-positive rates.
  • Improved target-tracking performance through feature engineering and model optimisation, documenting model limitations and deployment considerations.

Research Assistant — Department of Engineering

University of Liverpool, Liverpool, UK

⟶

Details
  • Contributed to a UKRI-funded Digital Twin project involving large-scale engineering simulation models.
  • Built tooling to make complex models usable outside the research environment via a web-based interface.
  • Published and hosted simulation models on AWS, enabling scalable public access to engineering model outputs.

Research Assistant

Imperial College London, London, UK

⟶

Details
  • Applied statistical and machine-learning methods to behavioural data in a high-risk policing context, supporting human-in-the-loop decision-making.
  • Explored and prototyped novel machine-learning methodologies through exploratory data analysis and rapid modelling to assess feasibility, limitations, and operational risk.

Education

PhD — Risk and Uncertainty in AI

Institute for Risk and Uncertainty, University of Liverpool, Liverpool, UK

⟶

Details
  • PhD research in risk science, applied statistics, and artificial intelligence, focused on uncertainty-aware decision systems in high-risk domains.
  • Designed and evaluated machine-learning models to characterise epistemic uncertainty, operational risk, and failure behaviour under data and model limitations.
  • Investigated how AI model outputs, uncertainty estimates, and risk signals affect downstream human decision-making.
Thesis
The Importance of Risk and Uncertainty for Humane Algorithms
Abstract
Algorithms have no idea of the significance of the calculations that they are performing. They just mindlessly output the results of complex mathematical operations, often requiring untenable assumptions to be made, irrespective of the risk posed by even simple errors, frequently in inhumane ways. My PhD argued that careful consideration of the uncertainties within systems and environments can aid ethical human-AI decision-making (especially under epistemic uncertainty) in high-risk scenarios. It was multidisciplinary in nature, spanning AI ethics, engineering, statistics and risk science.
Liverpool Repository

BSc (Hons) Physics with Theoretical Physics

University of Nottingham, Nottingham, UK

⟶

Skills

Machine Learning & AI
Supervised and unsupervised learning, anomaly detection, behavioural modelling, model evaluation, calibration, uncertainty quantification
Programming
Python (NumPy, pandas, scikit-learn, PyTorch, TensorFlow), JavaScript, SQL
Cloud & Deployment
AWS-based deployment, Docker containerisation, reproducible ML pipelines
Data & Statistics
Time-series analysis, feature engineering, statistical modelling, exploratory data analysis

Awards

Award Event Location Year
Best Presentation Liverpool Institute for Risk and Uncertainty Showcase Conference Liverpool, UK 2022
Student Merit Award (Risk Policy & Law) SRA Annual Conference Arlington, VA, USA 2019
International Student Travel Award SRA Annual Conference Arlington, VA, USA 2019
Shortlisted for Best Student Poster Award European Safety and Reliability Conference Hannover, Germany 2019

Projects

Deployment of AI in Medicine

  • Researched how AI-based clinical decision support systems (CDSS) are currently deployed in healthcare settings.
  • Highlighted that current performance evaluation mainly uses ROC-AUC and confusion-matrix metrics, with minimal assessment of how uncertainty presentation impacts clinical decision-making.
  • Concluded that while AI-CDSSs can improve decision speed and quality, many deployed systems inadequately communicate uncertainty, potentially impacting clinician trust and accountability.
  • Recommended further research to establish best practices for clear and intuitive risk and uncertainty communication in clinical AI.

Data Analysis for Sleep Study

  • Developed and applied generalised linear models to examine bidirectional links between sleep quality and mood in day- versus night-shift nurses.
  • Found evidence to suggest that night-shift workers have different self-reported sleep metrics and this has an impact on their mood and mental health.
  • These results have provided evidence for future funding applications for further research into shift work and mental health.

Dam Break Simulator

  • Designed and implemented a web front-end in JavaScript/Flask to visualise tailing dam collapse in Brazil.
  • This enabled citizen scientists to explore the risk to their communities.
  • Hosted on AWS and accessible at http://18.134.191.205:5000/.

PBA-for-Python

  • Designed and developed a Python module for probability bounds analysis, transforming prototype code into a production-ready pip-installable package.
  • Published and maintained the library on GitHub and PyPI, ensuring accessibility and version management for research and industry use.
  • Authored user documentation on Read the Docs.
  • Provided support for colleagues using the library in their research, demonstrating strong communication and collaboration skills in cross-disciplinary research.
  • GitHub: github.com/Institute-for-Risk-and-Uncertainty/pba-for-python
  • Docs: pba-for-python.readthedocs.io

Human-in-the-Loop Machine Learning

  • During a 6-month research assistantship at Imperial College, co-authored a literature review assessing how human-in-the-loop systems can be classified based on papers published within the last 10 years.
  • This literature review considered the following questions: What roles and actions do humans perform within HITL systems? How is the performance of the system assessed? And what areas of future research are there within this field?