Experience

• Geometric Deep Learning: Developing geometry-aware learning frameworks for structured and non-Euclidean data.

• Riemannian Optimization: Investigating manifold-based optimization and geometric methods for ML & DL.

• Geometryfor AI: Exploring differential-geometric representations, kernels, and optimization techniques for robust and interpretable learning such as for healthcare. 

• Awarded the Translational Research Fellowship to translate AI4ALZ & EEGSync into a deployment-ready clinical AI platform for Alzheimer’s disease diagnosis.

• Advanced the system from TRL 5 to TRL 7 through prospective multi-site clinical validation, robustness evaluation, regulatory preparation, and pilot clinical deployment. 

• Collaboraed with clinicians and hospital partners to enable real-world adoption of AI-powered EEG-based diagnostic systems and uncertainty-aware clinical decision support. 

• Led the design and development of AI-driven medical data systems, focusing on scalable machine learning and deep learning solutions for healthcare applications. 

• Managed end-to-end model pipelines, including data preprocessing, model development, optimization, and deployment. 

• Collaborated closely with medical practitioners and doctors to translate clinical requirements into robust, interpretable AI solutions for real-world healthcare applications. 

Selected as PhD Mentor for the SIDDHI (Summer Internship for Data-Driven Healthcare Innovations) program to contribute to funded healthcare AI research initiatives and to mentor undergraduate researchers. 

• SIDDHI 4.0 (Dec 2025– Feb 2026): AI-powered platform for accessible neurodegenerative disease diagnosis using MRI(03 students). 

• SIDDHI 3.0 (Apr 2025– Jul 2025): Early detection and multiclass classification of Alzheimer’s disease using EEG data (03 students). 

• SIDDHI 2.0 (Aug–Sep & Oct–Nov 2024): Data-driven EEG analysis for neurological disorders (02 students). 

• SIDDHI 1.0 (May– Jul 2024): EEG-based Alzheimer’s disease detection (05 students). 

Key Role: In research design and implementation, including EEG and MRI data preprocessing, feature engineering, development of ML/DL models, performance evaluation, and mentoring students. 

Research Outcomes: 03 patents (01 published, 01 filed, 01 under preparation) and 02 research papers (EEG-based study submitted; MRI-based study under development)