I build, lead, and develop a team of incredibly talented data scientists, while modelling excellence as an individual contributor. I am involved with and responsible for tactical and strategic business decisions regarding our research, products, customer support, sales, and marketing. I also run the new product research and development process for our organisation.I establish and evangelise AI best-practises, anticipate business needs, and keep up-to-date with and incorporate the latest technology and management trends across industry. I also communicate my vision to stakeholders from the members of my team to the executives, as well as represent Kount as an innovator in AI to our customers, industry analysts, and a broader audience at conferences.

I exploit Kount’s rich data set with machine learning algorithms to provide certainty in digital interactions, by identifying and preventing fraudulent ecommerce transactions for our customers.I work with a cross-functional team of developers, operations and quality assurance engineers to develop and deploy machine learning models and artificial intelligence in a real-time production environment. I independently pursue research tasks to improve and integrate our main products -- novel and state-of-the-art artificial intelligence algorithms with a high-availability, scalable platform, automating the path from data to decisions.

I develop computational tools to assist in the exploration of organic semiconducting materials, particularly with regard to their self-assembly properties and subsequent charge-transport characteristics. To accomplish this, I use a combination of molecular dynamics simulations, quantum chemical calculations, machine learning, and kinetic Monte Carlo simulations.The systems take the form of an interconnected network with millions of nodes and tens of millions of edges in total, corresponding to 100sGB of raw data.These simulations help explain phenomena that have been discovered through spectroscopic techniques, as well as engineer a set of design rules to help manufacture cheaper and more efficient organic electronic devices - and important step in producing reliable, sustainable energy for our future.* Designed, developed, published, and maintained the field's first coherent computational pipeline crossing lengths-scales from Angstroems to Microns.* Improved accuracy of carrier mobility predictions by 3-6 orders of magnitude over previous best-in-class record.* Developed efficient machine learning algorithms to model and predict electronic properties of molecules using artificial neural network and random forest techniques, improving computational throughput by 150%* Computational

I use Monte Carlo simulations to examine the charge generation and separation dynamics of carriers in organic photovoltaic materials. I examine the effect of complex bulk heterojunction morphology on the power conversion efficiency of such solar cells (particularly with regard to the role of molecularly mixed phases at both the molecular geometry and the charge transport levels). This, in turn, will help define design rules for high-performance organic photovoltaic devices.* Analysed hundreds of simulated electronic devices (> 500 GB of raw data)* Examined key phenomena and predicted new morphology-performance relationships* Predicted device efficiency characteristics for networks containing hundreds of thousands of particles* Obtained state-of-the-art charge-transport prediction accuracy for the complex systems considered* Computational