Open to opportunities

Poornachandra DH

@poornachandradh

Message

AI/ML-focused researcher building Deep Learning, NLP, and Healthcare AI solutions.

India

Message

What I'm looking for

I’m looking for a role where I can build and ship AI systems end-to-end—especially Deep Learning, NLP/RAG, and real-world healthcare or safety use cases—with strong engineering ownership, mentorship, and measurable impact.

I’m a third-year Information Science student at PES College with hands-on experience in Deep Learning, NLP, and Healthcare AI. I’ve built an end-to-end heart sound classification system (RDLINet) on the PhysioNet 2016 dataset, achieving 88.77% test accuracy and 96.92% AUC.

I also developed a Retrieval-Augmented Generation (RAG) system using LangChain and vector databases for intelligent document retrieval. Through projects like ResearchLens and my helmet detection system, I enjoy turning real-world problems into reliable AI pipelines, from data preprocessing and training to fast, citation-backed retrieval and deployment.

Experience

Work history, roles, and key accomplishments

AI/ML Research Intern

IndiTronix AI Labs

Nov 2025 - Apr 2026 (5 months)

Built an end-to-end deep learning pipeline for heart sound binary cardiac screening using the RDLINet architecture, achieving 88.77% test accuracy and 96.92% AUC. Engineered signal preprocessing (DFT baseline removal, overlapping snippet segmentation, Mel spectrogram generation), prevented data leakage via strict file-level splits, and improved generalization using early stopping and ReduceLROnPla

Deep Learning Heart Sound Classification RDLINet Signal Processing Early Stopping ReduceLROnPlateau