I am a final-year student in Robotics and Mechatronics Engineering at the University of Dhaka, working at the intersection of intelligent systems, multimodal AI, and real-world decision support. My research focuses on designing scalable AI solutions that translate advanced machine learning methods into practical applications across healthcare, agriculture, and critical infrastructure.
I currently hold two concurrent research positions — as a Research Assistant at Cortex AI Lab and a Research Intern at the Data and Design Lab (CARS). At Cortex AI Lab, my work centers on multimodal and agent-based AI, including vision-language systems for biomedical reasoning, visual question answering, and structured diagnostic support. At CARS, I develop large-scale data analytics and machine learning pipelines for power system monitoring, failure prediction, and reliability assessment using nationwide electricity and consumption data.
My broader research interests include multimodal learning, biomedical AI, agentic systems, and trustworthy AI. I have contributed to projects spanning plant disease diagnosis, vision-language benchmarking, power quality assessment, and autonomous robotic systems. I currently have research papers under review at major venues, including Nature Scientific Data and ICML 2026, and one paper accepted at ACL 2026 Findings.
- Conduct research on agentic AI and collaborative multi-agent systems, focusing on coordinated reasoning, task decomposition, and autonomous decision-making in complex environments.
- Develop multimodal biomedical AI systems integrating vision and language for clinically relevant tasks such as:
- Visual Question Answering for medical images
- Differential diagnosis support from imaging and clinical context
- Automated radiology report generation
- Design and evaluate medical vision-language pipelines for robustness, interpretability, and clinical usability.
- Investigate architectures that combine agent-based reasoning with multimodal perception, enabling structured clinical reasoning workflows and human-aligned decision support.
- Led large-scale analysis of power quality and reliability across multiple power distribution regions in Bangladesh.
- Processed and modeled heterogeneous data sources including:
- Power quality meter data
- Load and consumption profiles
- Industrial and consumer billing records
- Developed machine learning pipelines for failure prediction, anomaly detection, early fault identification, and load/demand forecasting.
- Built automated data engineering and model deployment workflows for scalable monitoring of power system health.
- Contributed to the development of an electricity-domain conversational assistant, enabling users to query billing issues, outages, and power quality concerns through natural language.
- Designed and implemented IoT-based robotic systems integrating microcontrollers, wireless communication, and real-time monitoring.
- Conducted structured training on robotics fundamentals, embedded systems, and algorithmic problem solving for competitive and research-oriented robotics.
- Developed embedded robotic systems using Arduino and ESP32 platforms.
- Designed industrial IoT solutions for monitoring, control, and automation.
- Implemented hardware-software integration for real-time sensing, actuation, and edge-level decision making.
- 🌍 Global Nominee — NASA Space Apps Challenge 2024
- 🥈 Runner-up — DU AI Challenge 2025
- 🥈 Runner-up — KUET Datathon 2025
- 🥈 Runner-up — Technocrats V2 IUBAT Hackathon 2024
- 🏅 Regional Champion — National High School Programming Contest (NHSPC) 2019
- 🎖️ Kaggle Expert — Multiple podium finishes in ML competitions Ongoing
