Mark Zolotas

Research Scientist in the Institute for Experiential Robotics at Northeastern University.

Postdoctoral Research Associate in the Robotics and Intelligent Vehicles Research Lab at Northeastern University.

Lectured for two Summer semesters the "Introduction to Machine Learning & Pattern Recognition" course offered in the Electrical & Computer Engineering department at Northeastern University. Constructed class material and complementary programming examples, which covered a broad range of topics and algorithms within machine learning.

Lectured and supervised various undergraduate/postgraduate modules in software engineering, robotics and artificial intelligence for the Department of Electrical and Electronic Engineering. The role required proficient C++ programming skills, keen understanding of the relevant technical concepts, as well as a strong passion for teaching and student learning support.

Operated under a multi-asset technology unit based in the Global Investment Management Solutions division. The role involved developing a new strategic portfolio management system for internal business users. My contributions included the design of a SQL database model for secure migration of the current framework into a production system environment, as well as the development of various financial applications in C#.

Developed multi-agent systems using a Java-based multi-agent simulation platform, called PreSage-2. Simulations of these systems were conducted to explore the effects of environmental protocols on reducing greenhouse gas emissions. My role also involved helping in organising the Self-Adaptive and Self-Organising (SASO) 2014 systems conference and designing the conference booklet using Adobe InDesign software.

Final Year Representative for Engineering Degree, 2015-2016 Vice Chair (Advertising & Sponsorship) of Cinema society, 2015-2016

Thesis topic revolved around learning a representation of human intentions during human-robot interaction and providing visual feedback via augmented reality to explain the resulting robot behaviours.