Bridging computer vision, clinical validation, and production-grade AI systems — from training models on histopathology datasets to deploying real-time diagnostic tools that clinicians trust.
Deep learning framework for whole-slide histopathology image analysis. Implements interpretable attention mechanisms and uncertainty quantification for clinical-grade diagnostic support.
Production-grade medical image segmentation pipeline with real-time inference, model versioning, and clinical validation metrics. Built for deployment in hospital environments.
Real-time monitoring system for diagnostic ML models with performance tracking, drift detection, and explainability interfaces. Provides clinicians with confidence scores and attention visualizations.
Peer-reviewed work on medical imaging, computer vision, and machine learning for healthcare applications. Focus on interpretability, uncertainty quantification, and clinical deployment.
I'm a software engineer and AI researcher focused on building reliable machine learning systems for medical imaging.
My work bridges computer vision, clinical validation, and production-grade software — from training models on histopathology datasets to deploying real-time diagnostic tools that clinicians can trust.
Previously, I worked on developing deep learning architectures for pathology image analysis and studied computer science with a focus on artificial intelligence. I care deeply about interpretability, reproducibility, and building systems that enhance rather than replace human expertise.
My research interests include uncertainty quantification in medical AI, attention mechanisms for interpretable diagnosis, and robust deployment of ML models in clinical environments.
Open to collaboration on research projects, open-source contributions, or consulting opportunities.