Hi, I’m Prakash Mallick, a researcher with a passion for topics related to control theory, machine learning, robotics, quantitative finance and data structures.

• As a Senior AI Quant Engineer and Researcher in the Institutional Banking & Markets systematic markets team, I specialize in developing technological solutions that transform financial trading processes:
  • machine learning systems for bond market analysis, creating predictive models that identify optimal counterparties for credit and non-credit high-grade bond transactions, enhancing trading decision-making precision
  • AI democratization initiative across multiple trading disciplines, including Quantitative, Commodities, and Interest Rate Derivatives (IRD) teams, bridging technological gaps and promoting data-driven strategies

• Currently a postdoctoral researcher at AIML, working with DSTG on producing capabilities at the intersection of machine learning and signal processing for real-time security and surveillance.
• Focus on analyzing RF spectrum to detect, identify, and generate models that can learn and generalize in real-time for out-of-distribution data.

• Worked as a quantitative researcher/engineer in the Research team at Ardea Investment Management.
• Collaborated with academics, economists, portfolio managers, and research analysts to deliver market-leading analysis for clients.
• Utilized statistical and machine learning research, computing expertise, and state-of-the-art optimization models to develop business tools and perform complex data analysis.
• Developed and implemented performant machine learning algorithms to deliver solutions to client requests.

• Graduated with a Ph.D. in Electrical Engineering, specializing in the intersection of optimal control theory and machine learning, specifically reinforcement learning applied to unknown dynamical systems, mainly in robotic applications.
• Carried out research on estimating control signal parameters in the presence of measurement noise, resulting in optimal policy with reduced uncertainty and better learning in model-based reinforcement learning frameworks.

• Contributed to the development of neuro-prosthetics for amputees in the Department of Mechanical Engineering.
• Worked on postural synergy modeling and control algorithms for an Allegro robotic hand.
• Featured on various Australian news channels for the work done: Link to video.

• Worked as an electrical excavation engineer at Coal India Limited.
• Optimized production processes using operations research concepts, resulting in reduced machinery usage, downtime, increased productivity, and cost savings.
• Developed mine plans prioritizing safety, efficiency, and cost-effectiveness through simulation modeling.
• Provided training and support for efficient operation of heavy engineering equipment like dumpers, loaders, and cranes.

• Ph.D. in Electrical Engineering from University of Newcastle, Australia in 2022
  • Research focused on optimal control theory and machine learning applied to unknown dynamical systems, mainly in robotic applications.
  • Worked on estimating parameters of control signals when the system has measurement noise to achieve optimal policy with reduced uncertainty and better learning when embedded in a model-based reinforcement learning framework.
• Masters of Engineering in Mechatronics from University of Melbourne in 2017
  • Introduced to the world of applied maths and operations research which led me to pursue a Ph.D. in optimisation and machine learning.
• Electrical Engineering from National Institute of Technology, Rourkela in 2012

• Linear and non-linear control theory
• System identification
• Supervised learning
• Deep reinforcement learning
• Stochastic optimal control
• Probabilistic inference
• Dynamics of robots
• Algorithms
• Data structures

Thank you for visiting my GitHub profile! Feel free to check out my repositories and projects, and don't hesitate to contact me for any questions or collaboration opportunities.