Mrinall Umasudhan
Research Assistant @Trustworthy Engineered Autonomy Tea Lab
Signup · Get unlimited contacts
WORK HISTORY
Research Assistant @Trustworthy Engineered Autonomy Tea Lab
Coauthoring a research paper that develops novel predictive models capable of forecasting a vehicle\'s safety status a defined number of seconds into the future.• Leveraged PyTorch to implement a robust predictor–evaluator pipeline utilizing Transformers and LSTMs, achieving a 94% accuracy rate in forecasting vehicle safety outcomes.• Leveraged Variational Autoencoders for feature extraction, capturing key latent representations to enhance model performance.
ABOUT MRINALL UMASUDHAN
As a Computer Science student at the University of Florida\'s Herbert Wertheim College of Engineering, I am driven by a passion for leveraging technology to solve complex problems. My academic foundation, coupled with hands-on experience in software development and research, has equipped me with a diverse skill set that spans from designing autonomous systems to developing user-centric web applications.I am currently deepening my expertise through a Software Engineering Internship at the University of Florida ECE, where I design and optimize web solutions to enhance faculty and student interactions. My work here has included leading a UI overhaul that improved loading times by 30% and automating critical data processes, reducing manual entry time by 95%.My previous experience as a Website Developer for the Competitive Programming Initiative allowed me to develop backend solutions that supported programming education for over students. By implementing performance-boosting algorithms, I reduced server latency by 40%, significantly improving the user experience.In addition to my internship experience, I contribute to research at the University of Florida’s Trustworthy Engineered Autonomy Lab and Machine Intelligence Lab. My work includes developing Variational Autoencoders for robotic scene analysis and enhancing unmanned submarine autonomy using advanced machine learning techniques.I thrive in environments that challenge me to innovate and push the boundaries of what’s possible with technology. My projects, such as an AI-powered baby monitor and an augmented reality-based billiards game, reflect my dedication to creating impactful and user-friendly applications.Let’s connect if you share an interest in cutting-edge technology and innovative software solutions!
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.