About Me

Researcher working at the intersection of AI safety, explainability, and policy.

I am currently working as a Senior Machine Learning Engineer at Ofcom in the algorithmic assessment team for Online Safety. My job focuses on how we can assess the algorithms behind social media platforms, especially recommender systems, to ensure people and mainly children, will not encounter harmful content so we can all have a safer online experience.

I have a PhD in Explainable AI (XAI) from City, University of London, where I also obtained my MSc in Data Science. My research focuses on developing interpretable deep learning neural networks that can produce human-understandable explanations while matching the prediction results of deep learning models. My PhD research is done as part of the SMART BEAR EU project that aims to develop a smart big data platform that will provide evidence-based personalised support for several pressing healthcare issues faced by the aging EU societies. My research therefore aims to utilise interpretable deep learning model to harness the power of both AI and XAI, and to enhance the reliability and acceptance of AI-based decision support systems in the healthcare domain.

Through PhD research in XAI and professional experience in the field, my experience spans developing interpretable ML models, conducting ML experiments, and providing technical expertise to policymakers to support informed and strategic AI regulation. I aspire to bridge the gap between advanced AI development and effective policy by assessing systemic risks, strengthening model safety evaluation frameworks, and contributing to evidence-based policies that enable the safe and responsible deployment of AI systems and create meaningful societal impact.