Machine Learning Intern
Current-- Collaborated with global ex-Meta team, deploying machine learning models in Python to build a scalable Digital Twin platform that simulates and optimizes real-world cellular networks for the Linux Foundation, improving network performance analysis by 15% and eliminating configuration testing costs by 70%.-- Created a Dockerized environment allowing clients to easily add personalized/customizable apps to Digital Twin (DT) platform with minimal infrastructure churn, reducing complexity and operational overhead by 20%.-- Designed and implemented Proof of Concept (PoC) apps/models for the Digital Twin-as-a-Service (DTaaS) platform by using Guass Markov mobility models to enable Bayesian Digital Twin, conducted Exploratory Data Analysis (EDA) to emulate different mobile user personas and enabled automated self-adjusting telecom infrastructure, demonstrating platform viability.-- Sole undergraduate intern on graduate-level intern team; demonstrated adaptability and resourcefulness by independently learning complex materials to effectively contribute to team. Contributed to open-source projects as part of workflow.