University College London // MSc science, technology, and society // sep 2025
The University of Texas at Austin // BBA in management information systems, certificate in computer science // may 2017
experience#
SaferAI // Research Scientist // April 2026 – present Working on the risk modelling team focusing on modelling AI-enabled cyber risk. Developing new risk models, setting baselines, interviewing experts
SPAR / SaferAI // Research Fellow, Quantitative Risk Modeling (Remote) // February 2026 – Present Refining quantitative risk-modeling methodology for AI-assisted cyber misuse by evaluating how benchmark performance maps to success across stages of the cyber kill chain.
UCL Centre for Responsible Innovation // Studentship and Research Assistant // mar 2025 – January 2026 Worked with Jack Stilgoe and Cian O'Donnovan on AI benchmarks. Synthesized research, mapped responsible innovation across departments, investigated PhD attitudes towards RI, supported communications.
Swimlane // professional services architect // May 2021 - Sep 2024 managed team of ps engineers, designed automation strategies, built python automations
healthAlliance // Senior Penetration Tester // Nov 2020 – Mar 2021 Managed pen testing pipeline, advised on remediation efforts, authored technical reports.
Protiviti // Senior Consultant // Aug 2017 - Oct 2019 oversaw junior consultants on assessments, led and designed testing programs, advised on RFPs
projects#
Dissertation: The Politics of AI Risk Assessment // Supervisor: Jack Stilgoe // Apr 2025 – Aug 2025
Research question: How are terms like ‘AI Safety’ defined and constructed, and how do they map to assurance activities like AI red teams and algorithmic audits?
Investigating our current suite of AI safety assessments, and in which direction these assessments push our conceptions of "safety" and "security".