About Me

Hi my name is Sajid, I am currently a Software Engineer at QuantumBlack as part of the Kedro team. Kedro is an open source python library designed to provide a framework for data engineers, data scientists and machine learning engineers a way to apply software engineering best practices when creating pipelines. I'm a recent MSc graduate looking to apply my skills in software engineering. My time at university has allowed me to gain key skills for this role through the various projects and experiences. You can view some of these below. During my industrial placment year I worked as a Software Engineer Intern at McAfee, the world's largest dedicated technology security company. This experience equipped with many skills including Linux, Perl, C++ and SVN.

Projects

  • rhNEAT

    My final year project invovled creating a new genetic algorithm by taking concepts from two existing algorithms namely, NEAT and RHEA, to create rhNEAT, Rolling Horizon NeuroEvolution of Augmenting Topologies, a new Statistical Forward Planning (SFP) method .

    Read More



  • McAfee Competition

    During my McAfee internship I was given the oppurtunity to participate in the annual McAfee School Coding Competition. Each intern was assigned a group of Year 12 students to create the best video game. I successully led my team to first place with our arcade style Connect4 game.

    Read More
  • Revenge of the Box

    As part of my Game Development module I led a team to create a 3D video game using the Unity engine and C#. Revenge of the Box is a third-person, isometric stealth strategy game. Players control a box that carries out several missions to infiltrate the ominous Company A.

    Read More

Publication

As part of the 2020 IEEE Conference on Games a condensed version of my dissertation was submitted for peer review. The paper was accepted and will be published in the conference in August 2020. I co-authored this publication with my supervisor Diego Perez-Liebana and Raluca D. Gaina. Click here to read this paper.

Abstract: This paper presents a new Statistical Forward Planning (SFP) method, Rolling Horizon NeuroEvolution of Augmenting Topologies (rhNEAT). Unlike traditional Rolling Horizon Evolution, where an evolutionary algorithm is in charge of evolving a sequence of actions, rhNEAT evolves weights and connections of a neural network in real-time, planning several steps ahead before returning an action to execute in the game.

Education

Queen Mary University of London:
BSc (Hons) in Computer Science with Industrial Experience: 1st class honours
MSc (Hons) in Artificial Intelligence: 1st class honours