I am a Master of Science student in Computer Science at New York University's Courant Institute of Mathematical Sciences, specializing in AI. My current research focuses on developing diffusion-based text-to-audio generation models under Magdalena Fuentes at MARL, NYU. I have contributed to the open-source Python library Soundata and have submitted our work to the Journal of Open Source Software (JOSS).

As an Applied Scientist Intern at Amazon, I worked on building advanced search systems for Amazon Music. This involved designing a robust, scalable embeddings-based retrieval system that improved search relevance by handling track title variations, artist abbreviations, and user query nuances.

I previously worked as a Machine Learning Engineer at Fortemedia - Nanyang Technological University (NTU) under the guidance of Dr. Rohan Kumar Das and Prof. ES Chng, where I engineered low-complexity acoustic event detection systems and developed multi-task learning frameworks for speech-to-text software. I also designed and deployed scalable, real-time infant cry detection systems.

Before that, I interned as a Software Developer at Bajaj Finserv Health Limited, where I developed personalized medication recommendation systems and scalable microservices for practice management systems.

I hold a B.E. (Hons) in Electrical and Electronics Engineering from Birla Institute of Technology and Science (BITS), Pilani and my research has been published in INTERSPEECH, APSIPA, DCASE and IEEE SSP.

Research Interests:
text-to-audio generative models, low-complexity models, recommendation systems, multimodal learning, and natural language processing.