Education
B.Sc in Software Engineering, Department of CSE
June 2021 to September 2025 at Islamic University of Technology - CGPA: 3.80/4.00
Work Experience
Software Engineer L-1
October 2025 to Present at Vivasoft Limited, Banani, Dhaka
- Built and trained a custom Bangla Text-to-Speech (TTS) model with an in-house curated dataset.
- Reduced training time of the in-house model by optimizing performance with CUDA programming.
Associate Software Engineer
June 2024 to September 2024 at Vivasoft Limited, Banani, Dhaka
- Developed and replaced GPT 4o based AI Image Search module with Vision Transformer based self-hosted model of an Indonesian e-commerce.
- Built a Shopify plugin chat-bot for product recommendation using GPT-3.5, Langchain, FastAPI, Pinecone Vector DB.
Software Developer Intern
April 2024 to May 2024 at Itransition Group, Remote
- Developed and deployed five applications using Ruby on Rails framework with secure authentication.
- Designed responsive and user-friendly frontend interfaces using Bootstrap framework.
Software Developer Intern
June 2023 to August 2023 at OpenGenus Foundation, Remote
Research Experience
Research Intern
March 2025 to Present at Advanced Machine Intelligence Research Lab, Remote
- Implemented federated learning and applied model pruning and quantization to improve efficiency and privacy in distributed training.
- Developed a lightweight classification model using depthwise convolutional networks, maintaining high accuracy for complex classification tasks.
- Enhanced skin cancer classification performance using ensemble techniques.
Bachelor's Thesis
October 2024 to Present at Islamic University of Technology
Title: Squeeze-Aware YOLO: An improved YOLO for Traffic Sign Detection
- Developed a lightweight novel object detection model based on YOLOv10, surpassing state-of-the-art models for traffic sign detection.
- Implemented and fine-tuned detection architectures for efficient real-time deployment.
- Enhanced and expanded an existing dataset of Bangladeshi traffic signs to improve model robustness and accuracy.
Publications
- PruneFedAD: Federated Learning with Structured Pruning for Low-Resource Alzheimer's Disease Detection
2025 International Conference on Decision Aid Sciences and Applications (DASA'25) - LeafLiteNet: A Computationally Frugal Interpretable Neural Architecture Under Controlled and Uncontrolled Environmental Conditions
Neural Computing and Applications (Springer), 2025. (Under Review) - A Survey to Understand the experience of ChatGPT Usage among Engineering University Students in Bangladesh
Technium: Romanian Journal of Applied Sciences and Technology (ISSN: 2668-778X), 2023
Achievements
- 2nd Runner Up: Streamstech presents IUT ICT Fest 2024 Code Catalyst: Refactoring Contest
- Awarded AWS AI & ML Scholarship out of thousands of applicants across the world.
- Winner at ML Olympiad: Tensorflow User Group Bangladesh by Google.
- Placed one of top 5 teams in CodeRush 1.0 Hackathon.
- Secured a place in top 50 of the Huawei Seeds For The Future 2024, Bangladesh.
Extracurricular Activities
Microsoft Learn Student Ambassadors
- Hosted and organized educational workshops focused on web development and delivered engaging presentations particularly on HTML, CSS, JavaScript, Git, GitHub, Django, Azure, and Python.
Talks and sessions
AI Adda at Vivasoft Limited
- Conducted a knowledge-sharing session for software engineers on integrating AI into software applications, covering key concepts such as Transformer architectures, LSTMs, and Reinforcement Learning with Human Feedback (RLHF).
Get started with web development using Visual Studio Code and GitHub Pages
- Delivered an engaging session on web development using Visual Studio Code and GitHub Pages, guiding participants through the full-stack development workflow, including IDE usage, version control, and deployment practices.
Projects
PolyVision: An end-to-end object detection pipeline on AWS for identifying plastic bags. Source Code
- Designed and implemented a scalable Object-Detection pipeline using SageMaker, Step Functions, and Lambda on AWS for batch image-based plastic detection.
LameLines: A platform to make people laugh. Source Code
- Built a dockerized joke-sharing platform in Go with PostgreSQL and Redis. Features include user authentication, email verification, joke sharing, comments, user following, and production-grade practices.
Jatra: A travel solution with hotel, transport, restaurant suggestions, AI blogging and photo search. Source Code
- Developed the AI-powered blog generation using Claude 3.5 Sonnet, image captioning with Claude 3 Opus, RAG-based image search with Pinecone Vector DB, and text embeddings with Voyage AI.
Software Fault Prediction System: A machine learning approach to detect software faults. Source Code
- Implemented 6 ML models on 3 defect datasets and gained a significant classification performance of 98-100% using SVM.
Technical Skills
Languages: Go, Python, Java, C++, JavaScript
Backend: FastAPI, Django, Node.js, Express.js
Frontend: React, HTML, CSS, Bootstrap
Databases: PostgreSQL, MySQL, Oracle DB, MongoDB, Pinecone, Redis
ML Technologies: Numpy, Pandas, Matplotlib, Seaborn, PyTorch, Tensorflow, Amazon SageMaker
Developer Tools: Postman, VS Code, Git and GitHub, Selenium, JMeter, AWS, Docker