About

Maggie Liuzzi is an aspiring AI Research Scientist with a passion for cutting-edge deep tech. With a Bachelor of Economics and a Master of Software Development, Maggie combines her skills in maths, statistical modelling, and engineering to drive strategy with data-driven, insightful research. Her previous roles in Business Development and Project Management have polished her communication skills and business acumen. Maggie is analytical, flexible, and highly resourceful, and loves exploring ideas and turning them into successful projects. Maggie's research interests include deep reinforcement learning, multi-agent interaction, inverse reinforcement learning, zero/few-shot and meta learning, self-supervised learning, imitation learning, user-intent detection, partial observability, lifelong learning, causality, and their applications in robotics, autonomous driving, policy making, quantum control, cognitive neuroscience, psychology, mental health, addiction, habit-forming, and nutrition. Currently, Maggie is a Machine Learning Engineer at q-ctrl, where she is researching and publishing on the application of novel machine learning techniques to solve challenging low-level/close-to-hardware quantum control, characterisation and optimisation problems, both in simulation and with physical quantum machines. She is implementing machine learning algorithms to solve quantum control problems faced by existing and potential customers, developing production-ready code and core product features that solve machine learning problems reliably, automatically, and at scale. Maggie is also providing technical capabilities for consulting engagements and constantly learning about new machine learning techniques and highlighting when they can benefit the product. In the past, Maggie has worked as a Perception Software Engineer at Baraja, where she processed, manipulated, visualised, and analysed the quality of point clouds using C++, Python, Numpy, and C#. She has also recorded and fused data from various sensors (LiDAR, Camera, GPS, IMU) using ROS (roscpp, rospy) and designed, user-tested, and implemented features for the in-house point cloud visualisation tool used by internal teams and external customers. Maggie has also created large pipelines for data storage using cloud computing (AWS: EC2, S3, Lambda), Docker containers, Flask, APIs, and bash scripts in both Linux and Windows, performed data visualisation and analysis (Python, Matplotlib, Power BI, Tableau, ERP: Odoo), and applied machine learning techniques (Python, Pandas, Keras, TensorFlow). Maggie has also worked as a Coding Tutor at Maggie Liuzzi | Freelancing, where she privately tutored a