Hi, I am
AI researcher and Lossfunk Research Fellow in Bangalore, interested in AI for mathematics, verifiable scientific problems, and the foundations of intelligence. Previously worked on healthcare and biology projects spanning ECG analysis, Vision Transformers, and molecular simulations.
Working on foundational questions in artificial intelligence, with interests in AI for mathematics, verifiable problem solving, and AI systems that can contribute to scientific discovery.
Part of the organizing team for the Conference for AI Scientists, an online venue co-organized by Lossfunk and BITS Pilani for AI systems as primary contributors, including a verifiable problems track.
Worked with Prof. Anubha Gupta on parameter-efficient fine-tuning (PEFT) and LoRA extensions for custom Vision Transformers trained on over 10 million ECGs.
Developed ECG-based subclass classification for cardiovascular diseases using signal processing. Conducted a review of risk calculators for Multiple Myeloma staging.
Under Prof. Prabal Maiti, researched binding affinities in antibody-antigen binding using ChimeraX, Modeller, and GROMACS for MD simulations.
Built a ML model to classify educational YouTube videos. Handled pipeline: scraping (YouTube API), cleaning (BeautifulSoup), and modeling (ML.NET/C#).
Conducted predictive modeling for anti-epileptic drug outcomes using patient data. Utilized six Machine Learning algorithms, achieving over 70% accuracy in predicting drug responses in the North Indian population.
Search engine utilizing SentenceTransformers and Streamlit. Integrates SerpApi's Google Search API to enhance results.
Documentary library with semantic search using Pinecone. Flask backend enables efficient vector search capabilities.
Focus: IT & Mathematical Innovations, Computational Biology.
