Chattogram, Bangladesh
Available for new work
AI/ML EngineerComputer Vision / NLP / Generative AI / Agentic AI
Building intelligent systems through AI research, machine learning, and generative AI.
Computer Science undergraduate and AI/ML Engineer with research experience, two IEEE conference publications, and hands-on experience developing RAG pipelines, Agentic AI workflows, and machine learning systems.
I'm a Computer Science and Engineering undergraduate at Patuakhali Science and Technology University with two IEEE conference papers and hands-on experience developing RAG pipelines, Agentic AI workflows, and machine learning systems.
I work mostly in PyTorch and FastAPI, with open-source LLMs fine-tuned using LoRA and QLoRA, and vector search with Qdrant. I'm interested in translating practical AI research and LLM architectures into efficient, real-world solutions.
Peer-reviewed work, with links to the published versions.
Open the research pageIEEE WIECON-ECE 2025 — First author
doi:10.1109/WIECON-ECE69386.2025.11526163
A hybrid ensemble machine learning framework for early-stage, real-time brain stroke risk prediction, with clinical decision support features that give healthcare practitioners data-driven predictive insights.
IEEE RAAICON 2025 — First author
doi:10.1109/RAAICON69033.2025.11502538
An IoT-enabled smart helmet that integrates real-time telemetry with road-condition monitoring, adding proactive accident prevention and alerts to improve rider safety and situational awareness.
2026 IEEE International Conference on Biomedical Engineering, Computer and Information Technology for Health (BECITHCON) — Third Author
Contributed to the development of DHT-Stack, a Deep-Hybrid Transformer Stacking framework designed for early and reliable dengue screening using routine hematological and clinical blood parameters. The research addresses critical challenges in traditional machine learning-based dengue screening, including class imbalance, false negative predictions, model interpretability, and prediction uncertainty. Key Research Contributions: Developed a hybrid stacking ensemble architecture integrating TabPFN, CatBoost, LightGBM, and XGBoost as Level-0 base learners. Applied SMOTEENN for handling class imbalance and improving the quality of training data. Utilized Boruta feature selection to identify 17 significant hematological biomarkers from 18 clinical parameters. Implemented cost-sensitive learning with a false-negative penalty of 5.0 to prioritize patient safety and reduce missed dengue-positive cases. Designed a Level-1 Ridge Logistic Regression meta-learner using out-of-fold predictions and stratified 10-fold cross-validation. Incorporated model disagreement-based uncertainty quantification to identify predictions requiring additional clinical review. Applied SHAP for global feature importance analysis and LIME for local prediction explanations. Evaluated model performance against standalone machine learning models using accuracy, precision, recall, and AUC-ROC metrics.
Systems I've designed and built, from research prototypes to full-stack products.
Browse all 8 projects
2026 — AI Engineering | LLM Engineering | RAG | Full-Stack Development
Built using RAG, FastAPI, React, Qdrant, and Groq, this project features intelligent document retrieval, reranking, real-time streaming, source citations, and JWT authentication.
The tools and methods I work with, grouped by area.
2026 – Present — Leadership
CSE Club, Patuakhali Science and Technology University
2022 – 2023 — Part-time
10 Minute School, Remote
2021 – 2022 — Volunteer
Apar's Classroom, Remote
2020 – 2021 — Part-time
Academic and Admission Pathshala, Remote
Patuakhali Science and Technology University, Patuakhali, Bangladesh
Expected graduation 2027CGPA 3.56
Patuakhali Science and Technology University
Ranked 29th among 93 competing teams.
Articles on AI, engineering and building products — what I built and what I learned.
Read all posts4 min read
How retrieval, reranking and a strict prompt turn an LLM into an IT helpdesk agent people can actually trust.
3 min read
Three.js, CSS perspective and a few rules that keep a 3D site fast on a normal laptop.
3 min read
A practical checklist for taking an AI prototype to something other people can use.
Open to AI/ML engineering roles, internships and research collaborations.
