AI Researcher & Engineer

IRFAN SADI DHRUBO

Architecting Intelligence for Tomorrow

Bridging the ethereal realm of artificial intelligence with real-world impact.
Carparkly AI Researcher | Epoch One Co-Founder

The Ascension

About Me

ISD

I am an AI Researcher at Carparkly, where I architect intelligent systems that push the boundaries of what machines can perceive and understand.

My work focuses on developing interpretable and responsible AI frameworks, particularly in healthcare applications. I believe in building AI systems that are not only powerful but also transparent, fair, and aligned with ethical guidelines.

As a co-founder of Epoch One, BRAC University's independent AI collective, I collaborate with brilliant minds to advance AI research and development, fostering innovation that transcends conventional boundaries.

AI
Research Focus
BRAC
University
2025
Active Year

Divine Arsenal

Skills & Expertise

Artificial Intelligence

Machine LearningDeep LearningNLPComputer VisionNeural NetworksResponsible AI

AI-Enabled Development

MLOpsModel DeploymentAPI DevelopmentAutomationData Pipelines

Programming Languages

PythonRustJavaScriptTypeScriptSQL

Infrastructure & DevOps

DockerKubernetesAWSCI/CDLinux

Research & Analytics

Statistical AnalysisCausal InferenceSHAP AnalysisBayesian Methods

Healthcare AI

Medical ImagingCardiovascular DiagnosticsInterpretable AIFDA/EU Compliance

Sacred Scrolls

Research & Publications

Featured Publication

Advancing Cardiovascular Disease Diagnosis with an Interpretable and Responsible AI Framework

Kazi Sakib Hasan, Irfan Sadi Dhrubo

A machine learning ecosystem developed to enhance CVD diagnosis through early warning systems and specialized diagnostic models. The framework leverages advanced ML techniques including TabNet, TabPFN, and ensemble methods, achieving 89% accuracy while incorporating interpretability tools (SHAP, counterfactuals), fairness mitigation, and uncertainty quantification. Aligned with FDA Good ML Practices and EU Trustworthy AI guidelines.

89%
Accuracy Achieved
+0.93
ST-Slope SHAP Value
0.36
Exercise Angina ATE
medRxivHealth InformaticsDecember 2025
Read Full Paper

Research Interests

Interpretable AIResponsible AIHealthcare MLCausal InferenceFairness in MLNeural NetworksCardiovascular DiagnosticsUncertainty Quantification

Establish Connection

Let's Create Together

Whether you're exploring AI research collaborations, seeking innovative solutions, or simply want to connect with a fellow traveler on the path of discovery.

“The measure of intelligence is the ability to change.”— Albert Einstein