E x p e r i e n c e

Aug 2024 - May 2026

Graduate Teaching Assistant

Miami University

Oxford, Ohio, USA

  • Graduate assistantship providing full scholarship for tuition and living expenses
  • Working on LLM and RAG (Retrieval-Augmented Generation)
  • Research on wheelchair accessibility solutions
  • Camera-mmWave fusion and machine learning detection for autonomous driving and road mapping
Python Java Machine Learning Deep Learning LLM RAG
Oct 2022 - Jul 2024

Software Engineer

Therap (BD) Ltd.

Dhaka, Bangladesh · On-site · Full-time

Career Progression:

Software Engineer:   Nov 2023 - Jul 2024

Associate Software Engineer:   Oct 2022 - Oct 2023

  • Played a key role in developing a scalable push notification framework, used by millions of users
  • Developed Excel upload/download solutions using internal frameworks, improving data entry efficiency by 80%
  • Implemented advanced archive and search functionality with internal frameworks
  • Developed database migration scripts
  • Conducted thorough code reviews, ensuring quality and best practices
  • Refactored legacy code using Java 8 features (Enums, Streams) and SOLID principles for better maintainability
  • Conducted code reviews to ensure clean coding standards and effective design patterns
  • Collaborated with project managers and senior developers to drive innovative solutions
  • Developed and presented an e-commerce website, showcasing training concepts

Tech Stack: Java Spring Framework, Hibernate, Oracle SQL, JSP, JavaScript, jQuery

Java Java Spring Framework Hibernate Oracle SQL JSP JavaScript jQuery
Jul 2022 - Sep 2022

Engineer I

Samsung R&D Institute Bangladesh

Dhaka, Bangladesh · Full-time · On-site

  • Passed Samsung's professional level test for employees
  • Worked on Samsung smart rings communication module

Tech Stack: Android Application Development, RTOS

Android RTOS

P r o j e c t s

MyPath Project
MyPath – Wheelchair-Accessible Routing Backend (NIDILRR Funded)

Nov 2024 – Present

Worked on Java Spring Boot API to generate wheelchair-accessible sortest routes based on latitude-longitude queries. Returns routes with surface type, incline, turns, and duration for optimized accessibility.

Java Spring Boot API Development Routing Algorithms Open Street Map   Visit our page
Mulitvendor e-commerce site
Mulitvendor E-Commerce Site

Jan 2023 – Apr 2023

A full-stack, role-based online store application built with Java, Spring, and Hibernate, which uses Docker for containerized deployment and a PostgreSQL database to manage e-commerce workflows for various user roles.

Java Spring MVC Hibernate PostgreSQL JSP Gradle Tomcat Docker   Project link
RU Contacts App
RU Contacts App (RU Funded)

2022

Developed a contacts app for Rajshahi University using Android Studio and Kotlin. Implemented MVVM architecture for better maintainability and scalability.

Android Kotlin MVVM   Google play link
Zero-Shot Crosswalk Detection Project
Zero-Shot Crosswalk Detection from GeoTIFF Data using Prompt Engineering

Nov 2024 – Dec 2024

Processed GeoTIFF satellite images and OpenStreetMap (OSM) data for analysis. Applied zero-shot learning with GPT-4o to detect crosswalks from high-resolution GIS imagery without labeled training data, achieving 97.5% accuracy.

Python GPT-4o Zero-Shot Learning Remote Sensing GIS   Paper link
Restaurant Management Project
Online Restaurant Management System

Jan 2023 – Apr 2023

Implemented order processing, table management, and user profile management with secure login. Ensured security with input validation, custom exception handling, and request filtering.

Java Spring MVC Hibernate PostgreSQL JSP Gradle Tomcat   Project link
Road Scalatonization Project
Road Scalatonization

March 2025

Developed a deep learning model to recover thin skeletons from thick, noisy road network images from OpenStreetMap (OSM). Used U-Net with residual blocks, iterative thinning, and multi-task learning for accurate skeletonization.

Python PyTorch U-Net Deep Learning Computer Vision   Project link
Human Activity Recognition Project
Human Activity Recognition & Ablastion Study

Oct 2024 – Nov 2024

This project detects human activities using form IMU sensor data. The dataset includes 15 users performing various activities. Features are extracted using a sliding window approach, and multiple models (Random Forest, XGBoost, CNN, Logistic Regression) are trained and evaluated. Random Forest, XGBoost, and CNN performed the best.

Python Scikit-learn TensorFlow CNN Random Forest Machine Learning Data Analysis   Project link
Urban Sprawl Detection Project
Urban Sprawl Detection (GIS)

Nov 2024 – Dec 2024

Analyzed urban sprawl in Dhaka using remote sensing and GIS with USGS data. Computed and visualized NDBI, SAVI, MNDWI, and IBI indices for land use assessment and spatiotemporal analysis of urban growth.

Python GIS Remote Sensing QGIS USGS Data Analysis Urban Planning   Project link

E d u c a t i o n

Aug 2024 - May 2026

MSCS in Computer Science

Miami University

Oxford, Ohio, USA

  • Awarded Graduate Assistantship with full tuition scholarship and living stipend
  • Awarded Summer Research Fellowship 2025
  • Member of Faculty Learning Communities - AI & Student Project Development (2025 - 2026)
Jan 2017 - May 2022

BSc. in Computer Science & Engineering

University of Rajshahi

Rajshahi, Bangladesh

  • Achieved the highest CGPA in the class for the 2016–2017 session
  • Dean’s List honoree, every 4 years of study
  • Ranked 6th in ITEE FE Exam taken by IPA of Japan
  • Member of the ACM ICPC community
2013 - 2016

Higher Secondary School Certificate

Sreepur Ramnagar Degree College

Rajshahi, Bangladesh

  • Major: Science

P u b l i c a t i o n s

2025

OmniAcc: Personalized Accessibility Assistant Using Generative AI

Authors: S. Karki, E. Han, N. Mahmud, S. Bhunia, J. Femiani, and V. Raychoudhury

Workshop on AI for Urban Planning, AAAI 2025 Workshop

Type: Workshop

AI Accessibility LLM Generative AI
2025

A Smart and Barrier-Aware Navigation System for Wheelchair Routing

Authors: ASM Mobarak Hossain *, Nadim Mahmud *, Ethan Han, Neil Advani, Bibodh Baral, Md Osman Gani, Vaskar Raychoudhury

Seventh International Workshop on Smart Living with IoT, Cloud and Edge Computing, IEEE MASS 2025

Type: Workshop

Accessibility ML Software Engineering

Contact Information

  Address

McVey Data Science Building 364, Miami University
Oxford, OH 45056
United States

  Office Hours

Monday – Friday
9:00 AM – 5:00 PM PST