Research Interests

My research interests fall under the broad umbrella of responsible AI, particularly:

• AI ethics
• AI governance
• evaluating large language models
• ethics artefacts to support AI design and responsible AI adoption
• bias, fairness, and non-discrimination
• human rights
• public sector algorithms

Selected Publications

To learn more about my research, check out my shortened list of publications below and the rest on my Google Scholar profile.

• Auditing a Dutch Public Sector Risk Profiling Algorithm Using an Unsupervised Bias Detection Tool, Second Conference of the International Association for Safe and Ethical Artificial Intelligence (IASEAI’26)
• Documenting Deployment with Fabric: A Repository of Real-World AI Governance, AIES '25: Proceedings of the 2025 AAAI/ACM Conference on AI, Ethics, and Society
• Bridging Research and Practice Through Conversation: Reflecting on Our Experience, EAAMO '24: Proceedings of the 4th ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization
• Not So Fair: The Impact of Presumably Fair Machine Learning Models, AIES '23: Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society
• Investigating the Legality of Bias Mitigation Methods in the United Kingdom, IEEE Technology and Society Magazine (Volume: 42, Issue: 4, December 2023)

Postdoctoral Research Fellow (FT)

I am working full-time on the PROBabLE Futures project at Northumbria University which is a Responsible AI (RAi) UK funded project. Within my first month of joining, I submitted to the Joint Committee on Human Rights’ inquiry: PROBabLE Futures Submission in response to the Call for Evidence on ‘Human Rights and the Regulation of AI’. In November 2025, I organised and led a multi-stakeholder workshop in London on what should be in an LLM evaluations framework for policing. My current work focuses on what robust technical and workflow level evaluations should be for policing AI systems as well as developing ethics artefacts to support the responsible adoption of policing AI systems.

Research Volunteer

I support the Centre for Emerging Technology and Security (CETaS) at the Alan Turing Institute on research projects relating to responsible AI and national security.

Independent Contractor

I work from time to time with the AI governance start-up, Immanence with building up their platform and on measuring social impact from AI projects. Research from my work at Immanence has been published in the Proceedings of the CHI 2026 Workshop: Ethics at the Front-End: Responsible User-Facing Design for AI Systems: Resisting Humanization: Ethical Front-End Design Choices in AI for Sensitive Contexts.

Director of Working Groups

I am a Director of the Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO) Bridges' working groups which bring together researchers and practitioners from around the globe to tackle real-world problems through online groups. I previously co-organised the Conversations with Practitioners working group from September 2023-July 2025. Through the CwP group, we published this ACM EAAMO '24 conference paper: Bridging Research and Practice Through Conversation: Reflecting on Our Experience.

Research Associate

I worked on a project relating to AI-assisted decision-making, uncertainty, and human-AI oversight. This work was part of the EU project, ELSA (European Lighthouse on Secure and Safe AI). In spring 2025, I co-organised an in-person panel event in London, How AI is shaping journalism and journalism is shaping AI. This AAAI/ACM AIES '25 conference paper on AI governance came out of my research: Documenting Deployment with Fabric: A Repository of Real-World AI Governance (see the appendix on Arxiv for the repository of use cases). In addition, my uncertainty and AI discrimination research was featured in the KU Leuven AI Summer School's blog: Uncertain AI Systems Can Be Discriminatory: How Can We Address This? I worked PT for 6 months and FT for 3 months due to visa reasons while waiting for my PhD conferral.

Bias Detection Tool Cohort Member

I joined a cohort working remotely on Algorithm Audit's bias detection tool. We applied the tool to a Dutch public sector use case and wrote our findings in an IASEAI '26 conference paper: Auditing a Dutch Public Sector Risk Profiling Algorithm Using an Unsupervised Bias Detection Tool.

Graduate Teaching Assistant

As a Graduate Teaching Assistant (GTA) for Machine Learning, I ran weekly labs and marked the coursework. I also led four labs and a couple of tutorials for Data Structures every few weeks; I marked for this course too.

As a GTA for Machine Learning, I ran two weekly labs and tutorials. In addition, I was the GTA for the AI Impact Accelerator module. I also led two tutorials and two labs for Data Structures every three weeks.

As a GTA for Artificial Intelligence, I ran two weekly online live tutorials where I made sure the students were confident with the material and the tutorial sheet answers. I also ran four virtual live labs each week where students worked on developing a successful pacman agent during the Autumn 2021 term.

As a GTA for Machine Learning, I ran two small group live sessions weekly for undergraduates covering the tutorial sheet for that week. I also was a GTA for the Big Data Technologies course. I ran three online live lab sessions weekly for masters students, helped answer any questions they had, and marked coursework.

PhD Mentor for DAAD Rise Worldwide

I hosted a German undergraduate student researcher over 8 weeks while she worked alongside me on my PhD research project. She was funded by the DAAD RISE Worldwide program. Our research was published in the AAAI/ACM AIES '23 conference: Not So Fair: The Impact of Presumably Fair Machine Learning Models.

PhD Intern

I completed a 5 month (~two days a week) PhD Placement at the CDEI (now the Responsible Technology Adoption Unit), enabling the trustworthy use of data and AI. I worked on two different projects: the Responsible Demographic Data and the Bias Review projects. For London Tech Week 2022, I co-authored a blog post about demographic data collection and bias detection. My research on the Bias Review project while at the CDEI later developed into this IEEE article: Investigating the Legality of Bias Mitigation Methods in the United Kingdom.

AI Robustness Researcher/Developer

Alongside three other PhD Student colleagues, I completed a literature review of AI Robustness methods, zoning in on NLP, weight-poisoning attacks, and poisoning detection methods. We developed a project combining state of the art AI Robustness and NLP research. I was the lead point person for communicating with our stakeholder, EY, every week over the 10 week project. To learn more about what we developed, check out our GitHub repository here: RobuSTAI.