As a Machine Learning and Computer Vision Engineer at Outrider, Inc, I spearheaded a project aimed at automatically extracting trailer IDs from parked trailers within a yard. My responsibilities encompassed the entire project lifecycle, from architecting the solution to deploying a functional prototype.Key Achievements:Architecture Decisions: I undertook the responsibility of choosing the optimal architecture and technical approach for the project. By assessing various methodologies, I selected an architecture that best suited our requirements, ensuring robustness and scalability.End-to-End Development: I coded, trained, and deployed a cutting-edge prototype on an autonomous vehicle (AV) platform. This process demanded attention to detail and a deep understanding of machine learning algorithms, enabling us to showcase progress even under tight deadlines.Model Enhancement: Aiming for continuous improvement, I orchestrated an initiative to refine the performance of our model. This involved leading a comprehensive data collection and labeling effort, resulting in a dataset that significantly improved our model's accuracy.Synthetic Data Generation: Recognizing the need for improved text recognition, I created a synthetic dataset of millions of labeled images of text. By designing this dataset to mimic real-world scenarios, I substantially improved our model's text recognition capabilities.Cross-Functional Collaboration: Throughout the project, I collaborated with diverse teams and product managers. By creating strong working relationships, I successfully orchestrated the creation of an innovative machine learning system that aligned with our business objectives.My role as a Machine Learning Engineer at Your Company Name exemplified my commitment to technical excellence, leadership, and cross-functional collaboration. Through this experience, I solidified my passion for leveraging machine learning to solve complex challenges while driving business success.

Drove innovation as a Machine Learning Research Scientist, contributing to a range of groundbreaking projects at the forefront of technology.Key Achievements:Algorithm Development: Spearheaded the development of a robust pipeline for few-shot learning, demonstrating how a two-model system can improve performance with extremely limited training data.Interdisciplinary Leadership: As Co-Principal Investigator (Co-PI), led an interdisciplinary initiative that harnessed machine learning to predict damage in large metal structures. Collaborated seamlessly across disciplines to deliver actionable insights.Grant Acquisition: Secured grant funding in a competitive internal competition for the impactful project "Foundations of Human Informed Machine Learning." Demonstrated visionary thinking and the ability to communicate the value of innovative research.Subject Matter Expertise: Took on the role of a machine learning Subject Matter Expert (SME) on a biology-focused project. Leveraged deep domain knowledge to bridge the gap between machine learning techniques and complex biological processes.My journey as a Machine Learning Research Scientist has been marked by a passion for cutting-edge technology, collaborative excellence, and a dedication to pioneering solutions that transcend boundaries. Through diverse projects and proactive leadership, I've consistently contributed to the forefront of machine learning research and its applications across various domains.

My research as a Research Assistant at the University of Memphis, centered around a critical objective: to accurately predict the maximum magnitude of potential induced earthquakes in the region. I developed an inverse problem so that I could use dynamic rupture modeling to study induced earthquakes in Oklahoma. As the dynamic rupture models are computationally expensive, I developed a machine learning model to serve as a metamodel or surrogate model to allow for the inverse problem. The results suggested that the induced earthquakes were of similar magnitudes as the naturally occurring earthquakes.