Tech Enthusiast
Undergraduate CSE student at North South University, passionate about building practical solutions with code, exploring AI & machine learning applications.
About
I'm Ibrahim Siddik, currently pursuing a BSc (Eng.) in Computer Science and Engineering at North South University (2022 - Ongoing). Before that, I completed my HSC at Sirajganj Govt. College in 2020 and SSC at B.L Govt. High School, Sirajganj in 2018, both with a science focus.
Over time, my interest in technology evolved from simple curiosity into a strong drive to build real, useful things from web apps to intelligent systems that can understand data and language.
I enjoy breaking down large problems into smaller, manageable pieces and approaching them methodically. Whether it's designing a database, implementing an algorithm, or deploying a full-stack application, I care about clarity, structure, and maintainability.
I like learning by doing: building projects, experimenting with new tools, and turning ideas into working prototypes.
At the core, I enjoy problem solving. I'm especially interested in how AI and machine learning can help in everyday digital experiences.
I’m always looking for opportunities to apply my skills to meaningful challenges, grow as an engineer, and contribute to teams that care about quality and impact.
Skills
Writing clean code for solving problems and building real-world applications.
Designing schemas, writing queries, and connecting applications to data storage.
Building and deploying web applications, focusing on usability, performance, and reliability.
Exploring intelligent systems that learn from data and understand language to make useful predictions.
Projects
A full-featured ticketing platform to improve the quality of mass transport in Bangladesh, covering metro, bus, and train services. Includes online ticket booking, seat selection, real-time updates, Google authentication, user profiles, admin dashboard, and reviews.
Designed to be a significant improvement over traditional manual ticket booking workflows.
A deep learning based system that classifies histopathological images into 5 cancer types through a web interface. Users can upload images and receive predictions powered by trained models.
Focuses on implementing a "Search Against Verifier" strategy for Large Language Models (LLMs). The core concept is to structure the inference process to improve reasoning capabilities. By implementing a "Reasoning While Decoding" pipeline,it utilizes Chain-of-Thought (CoT) prompting combined with Self-Consistency (Majority Voting) to ensure more accurate model outputs.
Designed to be a significant improvement over automatic inference.