About me


  • I am a Machine Learning Engineer @ BenevolentAI, an AI research company working on applying machine learning to the drug discovery and development process.
  • My research interests lie at the intersection of computer science and economics including the general area of machine intelligence and reinforcement learning as well as deep learning and natural language processing (NLP). I am particularly interested in multi-agent learning, generative adversarial networks (GANs), cooperation and coordination problems, preference modelling, mechanism design, the theory of mind and combining all of the above to establish intelligent systems which can reason and act in complex environments.
  • I received my Bachelor’s degree from University College London (UCL) where I have graduated with a first class honours BASc degree with distinction (Dean’s List), majoring in computer science and minoring in economics. My dissertation focused on Multi-Agent Reinforcement Learning in sequential social dilemmas and was advised by Prof. Jun Wang and Dr Manuela Dal Borgo.
  • Previously I enjoyed working at Autonomous Agents Research Group at the School of Informatics, University of Edinburgh, supervised by Dr Stefano Albrecht where I was researching stabilizing Generative Adversarial Networks training and 2 amazing start-ups; Growbots (advised by OpenAI’s co-founder) and Plural AI (backed by Entrepreneur First) where I did some NLP & engineering work.

Recent News

  • Joined BenevolentAI, a research company focused on applying AI to the drug discovery problem as Machine Learning Engineer, where I will be working on NLP alongside an amazing team of researchers, engineers and bioinformaticians. [02.12.2019]
  • Gave a talk on Learning to cooperate with Multi-Agent Reinforcement Learning on ML in PL conference. University of Warsaw. [23.11.2019]
  • Received Best Talk - People’s choice award for my talk on “Learning to cooperate - the emergence of sustainable resource management among artificial intelligence agents” at Science: Polish Perspectives (SPP) conference. Cambridge 2019. [09.11.2019]
  • I have submitted an early draft of my survey on stabilizing GAN training to arXiv. You can see it here. Please get in touch if you have any feedback. [02.10.2019]
  • My application for a talk on “Learning to cooperate - the emergence of sustainable resource management among artificial intelligence agents” to Science Polish Perspective (SPP) conference at the University of Cambridge has been accepted and will take place between 8th and 9th November 2019. [17.09.2019]
  • I will be going to Edinburgh to work as a Research Intern at the Autonomous Agents Group, School of Inormatics, University of Edinburgh under the supervision of Dr Stefano Albrecht on stabilizing Generative Adversarial Networks (GANs) training. [12.09.2019]