Computer Science graduate and Junior Software Engineer with professional experience in developing, maintaining, and debugging production-level software applications. Proficient in Python, C#, Dart, and backend development, with hands-on experience building RESTful APIs, integrating databases, and implementing scalable application architectures. Experienced in ASP.NET Core, FastAPI, Entity Framework, Git-based collaborative workflows, and Docker. Additionally, have practical experience developing Python-based machine learning systems and integrating predictive models into application backends. Strong foundation in data structures, algorithms, object-oriented programming, and software engineering principles, with a keen interest in AI infrastructure and data-driven systems. — Publication: Hybrid ML-SLM RAG System for Large Technical PDFs (IEEE Conference Publication) — contributed to research investigating a hybrid machine learning and Small Language Model (SLM) based Retrieval-Augmented Generation (RAG) system for large technical PDF documents. — Undergraduate Thesis (BRAC University): Advanced Machine Learning Techniques for Personalized Alopecia Areata Intervention Modeling — conducted machine learning research involving multiple datasets, predictive modeling, explainable AI, feature engineering, dataset integration, and a hybrid CNN-autoencoder architecture. — Project: Alopecia Factors Detector — web application with a Python-based machine learning backend to analyze medical and lifestyle factors associated with hair-loss risk (Cloudflare Pages, Render). — Project: FIFA 2026 Live Score Tracker — real-time match tracking app in Flutter with Riverpod and Dio; 100+ downloads on GitHub. — Project: Library Management System — RESTful ASP.NET Core system with N-Layer Architecture, Repository Pattern, MediatR CQRS, JWT, RabbitMQ via MassTransit, Elasticsearch and Docker Compose. — Project: Freight Rate Prediction — end-to-end Python machine learning project comparing LightGBM and CatBoost with time-based validation.