About Me

I'm a machine learning researcher and quantitative professional with a passion for bridging cutting-edge research and practical applications in quantitative finance and energy markets.

Current Role

I currently work as a Deal Structurer at Shell Trading & Supply in London, where I leverage my skills in machine learning and analytics for the structuring and valuation of natural gas and LNG structured assets, as well as long-term bilateral deals.

Professional Journey

Before joining Shell in 2024, I spent five years at J.P. Morgan Chase, progressing from Research Intern to VP Machine Learning Lead. During this time:

  • I was the lead ML researcher for Deep Hedging initiatives for Equity Derivatives. The project was already in production when I joined; I was responsible for achieving over 2x training performance improvement. I also developed robust frameworks for transitioning research code to resilient production systems.
  • I used NLP methods like tokenization and preprocessing techniques to optimize large-scale risk calculations (patent pending).
  • Prior to that, I worked on privacy-preserving machine learning (3 patents and two research papers).
  • For my research output and the number of patents filed, I was recognized as J.P. Morgan Chase Prolific Inventor (class of 2023).

Research Background

I completed my PhD in Computer Science at Imperial College London (2016-2020), focusing on probabilistic models for data-efficient reinforcement learning under the supervision of Marc Deisenroth. My research explored:

  • Data-efficient reinforcement learning with Gaussian Processes
  • Probabilistic Model Predictive Control
  • Uncertainty quantification in non-linear dynamical systems
  • Safe model-based RL for robotics and control

During my PhD, I also worked as a Machine Learning Researcher at PROWLER.io in Cambridge (2018-2019), applying GP-based methods to real-world reinforcement learning problems.

What I'm Looking For

I'm interested in opportunities that combine my research expertise with quantitative applications, particularly in:

  • Quantitative Finance: ML for trading, hedging, and risk management
  • Energy Markets: Analytics for structured products and commodity trading
  • Research Collaboration: Applied ML research in finance or energy sectors
  • ML Leadership: Building and leading teams that deliver production ML systems

Research Interests

My core research interests include:

  • Reinforcement Learning & Optimal Control
  • Gaussian Processes & Probabilistic Modeling
  • Variational Inference & Bayesian Deep Learning
  • Production ML Systems & MLOps
  • Quantitative Modeling for Financial Applications

Beyond Work

I'm passionate about making machine learning research accessible and impactful. I've been involved in organizing Machine Learning Summer School (MLSS 2019) in London and Imperial's WOHL outreach lab, conducting demos and debates on AI ethics to encourage students from disadvantaged backgrounds to pursue careers in robotics and machine learning.