Building a scalable cell classification model for T4 vs B cell and T8 vs B cell, leveraging Knowledge Distillation for speed optimization and Transfer Learning for zero-shot inference capabilities. The final deployment is planned for FPGA to enable real-time T-cell detection.

Constructed a Transformer-based model for accurately predicting cell trajectories in microfluidic devices, focusing on the optimization of designs such as deterministic lateral displacement (DLD).

Implemented an Excel VBA-based line balancing algorithm to address worker absenteeism and optimize production efficiency at GMS Composite Knitting Ind. Ltd., the largest facility in Bangladesh with 17,000 workers.

Created an algorithm to accurately predict color consumption in T-shirt printing for Thanbee Printing Plant Ltd, achieving greater than 99.5% accuracy by calculating intricate design areas using Photoshop.

Developed a particle sifting machine during a course project, which gained interest from BUET Foundry Lab for use in mold sand preparation.