• Developed and deployed a voice-based automation system for cataloging, billing, and ordering workflows on GCP, integrating advanced NER and transcription models to support over 10 Indian regional languages.• Collaborated with cross-functional teams to integrate the system with Android and iOS apps, achieving a 20x efficiency improvement compared to LLM-based automation.

• Generating synthetic audio data for various Indian language accents to enhance speech recognition training datasets.• Fine-tuning the Whisper model to optimize performance for specific speech recognition use cases.• Developing APIs to integrate advanced speech recognition functionalities into existing systems.• Assisting with the deployment of models to ensure seamless integration and operational efficiency.

• Successfully led and executed various machine learning projects, delivering substantial accuracy improvements in bike sharing demand prediction, handwritten digits classification, landmark Classification & tagging for social media, and developed a comprehensive ML workflow for Scones Unlimited on AWS SageMaker.• I Was among the top 10 finish-line winners in the first cohort of 1000 AWS AI and ML scholars from 80 countries , and for that, I was chosen to get a reward.

• Developed and deployed CorrSpell, a spelling correction tool, and authored comprehensive design and architecture documents, demonstrating proficiency in end to end development and documentation.• Designed user-friendly wireframes and applied innovative problem-solving skills, contributing to the success of the CorrSpell project while adhering to industry standards.