Software Engineer, Machine Learning Engineer, Undergraduate Researcher

PAPA MANU

Baltimore, MD 302-***-**** ******@****.*** linkedin.com/in/papa-manu-41a5b827b

EDUCATION

University of Maryland, Baltimore County- Bachelor of Science, Computer Science, GPA (3.76) Meyerhoff Scholarship Recipient

Data Structures, Object-Oriented Programming, Discrete Mathematical Structures, Computer Organization, Computer Architecture, Linear Algebra, Statistics, Intro to AI/ML, Operating Systems, Software Engineering Languages: Python, C++, C, Java, Haskell, HTML5, CSS, Matlab, Assembly Technical Tools: Linux, Windows, Visual Studio Code, Tenable, Splunk, CrowdStrike Other Skills: Machine Learning, Clustering, 3D Modeling, Affiliations: NSBE

Led research on parallel algorithms for high-dimensional clustering, driving breakthrough performance improvements that resulted in a 96x speedup of the K-means algorithm for large-scale data sets. Developed computational techniques to enhance algorithmic scalability, pushing the boundaries of AI and ML in solving real- world, data-intensive problems.

Contributed to a 30% reduction in computational time for high-dimensional clustering tasks, advancing the application of AI/ML in solving real-world, data-intensive problems.

Optimized system performance by 25% by enhancing existing software and implementing new features, improving user experience and system reliability across Delaware’s state network systems. Enhanced system performance by optimizing existing software and implementing new features to improve user experience and system reliability.

Led the integration of software tools, optimizing system performance while ensuring stringent protection standards, contributing to improved operational efficiency and cybersecurity defense mechanisms across state networks. Engineered and optimized Python-based preprocessing and tracking pipelines, reducing model training time by 35% through more efficient data augmentation and GPU utilization. Participated in full-cycle software development including feature development, debugging, code review, and version control using Git

Developed and evaluated pose estimation models using Pytorch, achieving a 15% increase in tracking accuracy on multi-animal datasets (mice, fish, and insects).

Collaborated on the development and optimization of SLEAP, an open-source deep learning framework for multi- animal pose tracking, adopted by research labs worldwide. Worked cross-functionally with neuroscience researchers and software engineers to ensure seamless integration of machine learning models into lab workflows.

Improved wildfire behavior forecasting accuracy by 20% through the development of AI-driven machine learning models Develop and deploy AI-driven machine learning models to generate real-time ensemble forecasts for wildfire behavior Implement satellite data assimilation techniques to enhance accuracy in wildfire and smoke impact simulations, improving predictive outcomes and decision support

Expected: May 2026

San Diego, CA

Wildfire Digital Twin (WDT) Project

EXPERIENCE

Machine Learning Engineer Intern Salk Institute of Biological Studies Undergraduate Researcher NASA

Software Engineer Intern Delaware Dep. of Technology AI/ML Research Intern National Science Foundation (NSF) June 2023-August 2023 August 2024 - May 2025

June 2024 - Aug 2024

May 2025 - Present

TECHNICAL SKILLS

LEADERSHIP & ACHIEVEMENTS

Best Computer Science Presentation Award Emerging Researchers National Conference

- Delivered an oral presentation of Parallel Algorithms for High-dimensional clustering Deans List UMBC

Meyerhoff Scholar Program Peer Advisor UMBC

Contact this candidate