About
I am a VP, Quantitative Analyst with a PhD in Applied Mathematics and deep expertise in AI/ML, credit risk modelling, and financial analytics. My work bridges quantitative finance, data science, and technology, helping organisations develop scalable, explainable, and efficient financial models.
At Barclays, I lead credit risk model implementation across retail and wholesale banking, optimising IFRS9, AIRB, and stress testing models. I built a Python-based model explainability framework, reducing execution time by 90% and enhancing ECL/RWA insights for key business decisions. Previously, I led the Open Banking ML project at a leading FinTech company, increasing loan approvals by 5% and reducing credit losses by 50%.
With expertise in Python, AWS, CI/CD, and big data analytics, I specialise in model deployment, DevOps, and financial AI applications. Passionate about mentoring and technical leadership, I contribute to Barclays’ Machine Learning Reading Club (2,000+ members) and internal engineering culture initiatives.
Beyond my day job, I co-organise the PyData London Meetup, a vibrant community of 15,000+ data enthusiasts, practitioners, and researchers. I help curate talks, foster collaboration, and build bridges across academia and industry to promote open source, applied ML, and real-world data science.
I am actively exploring opportunities at the intersection of AI, finance, and risk modelling, where I can leverage my expertise to drive innovation and business impact.