Experience

---

Lacra Pavel's Research Group

Research Assistant

August 2023 - May 2024

• Working on improving Nash Equilibrium-seeking techniques using Reinforcement Learning by utilizing Q-Learning and Passivity-based Control in both continuous and discrete time to optimize convergence to stable Nash Equilibrium in hypo monotone games

University of Toronto

Teaching Assistant

September 2023 - December 2023

• Teaching Assistant for: Introduction to Programming (ESC180) in Python, Algorithms & Data Structures (ESC190) in C

Walmart

AI Efficiency Engineer

January 2023 - September 2023

• Collaborating with various teams such as Marketing, Finance, Replenishment, etc. to create an efficient promotions process via an AI-based approach using AWS, React, Typescript, and Python
• Mobilizing the use of AI-reliant tools in the workplace by creating a Neural Network to complete price entries on flyers

Max-Planck Institute

Software Engineer Intern / Research Associate

May 2021 - August 2023

• Cultivating a GUI and server-based system for the University of Hamburg and MPI to use for virtual experiments at the University of Hamburg Implementing an SQL database to handle several IP addresses, ports, and client data

University of Toronto

Engineering Consulting Association

Team Lead

September 2021 - April 2022

• Working with FLAPCanada, created a Binary classification Neural Network to classify if a window is safe for birds or not and deployed it as a web application for users to identify if their windows are safe

Content Turbine

Software Engineer (Freelance)

December 2020 - September 2021

• Built NoSQL datastore and caching modules for the Akka Play! and Vert.x frameworks in Java using Singleton and Dependency Injection (DI) design patterns, and reactive programming, with Guice and JUnit unit testing

Projects

---

Discrete-Time Heavy-Anchor Reinforcement Learning in Multiagent Finite Games

September 2023 - May 2024

• Spearheading cutting-edge research into Nash Equilibrium-seeking techniques using Reinforcement Learning
• Utilizing techniques such as Q-Learning and Passivity-based Control in both continuous and discrete time to optimize convergence to stable Nash Equilibrium in hypo monotone games

Optimizing Operation Room Scheduling Sunnybrook Trauma

December 2023

• Worked alongside Sunnybrook Trauma to create various models such as LSTMs, Sarima, Neural Prophet, and various regressions to predict trauma volume by hour and severity per day

Adaptive Mechanical Stage Diagnostics Tool

September 2022 - December 2022

• AMSaD streamlines malaria diagnosis using an adaptive stage and a CNN-based Diagnostics Tool, enhancing testing efficiency for eHealth Africa (eHA)
• AMSaD targets Nigeria's malaria challenge by optimizing healthcare procedures with advanced technology, aligning with eHA's mission and addressing specific stakeholder needs
• AMSaD emphasizes integrating the adaptive stage onto existing microscopes and selecting relevant training data for the CNN-based Diagnostics Tool, ensuring effective malaria diagnosis within eHA's healthcare system

Price Tracker Web Scraper

July 2022

• Created a user interface to interact with a system that automatically scrapes, tracks, and updates prices utilizing SQL
• Utilized React, Flask, and Playwright to create a UI for the user to interact with, and Bright Data to scrape values from Amazon

Recidivist Predictor Project

January 2022

• Analyzed the COMPAS dataset historical data to examine the probability of an offender to commit another offense
• Examined the False Positive Parity of predicting recidivism based on race while excluding demographic information
• Created an Adversarial Learning Procedure to counter-predict against the initial regression model predictions