Experience

• DATA SCIENTIST | 12/2020 - 04/2022 | Policybazaar Inc | India

• Developed predictive models using machine learning, natural language and statistical analysis methods.
• Trained a Large Language Model BERT from scratch for Hinglish Dataset.
• Used the above LLM to finetune a Question Answering model to extract entities profession, income, date of birth,education from Audio Speech Recognitions transcripts.
• Built compelling data stories and visualizations to influence decision makers.

• DATA SCIENTIST | 09/2019 - 12/2020 | GEP Worldwide | India

• Train, test and deploy in production NLP and big data based models which serve 10-15 high premium customers.
• Built and deployed a text classification system that would take in a line description and classify it into the 16000 different classes with accuracy of close to 85%.(Patent, refer publications).
• Single-handedly built and deployed automated news gathering based on specific search words around clients and return important and recently published news articles.
• Built and deployed for multiple clients including pharma orgs Algorithms:( LDA-Based Topic Modelling, SIF Based Text Summarization).

• DATA SCIENTIST | 09/2016 - 08/2019 | Gainsight Inc | India

• Train, test and deploy in production NLU(Sally Gainsight) and churn models.
• Implemented question answering T2T bot Layer which recognized entities and intent from a question on slack.
• Framework: RASA-NLU Algorithm : BiLSTM + CRF.
• Conduct a thorough investigation of data and build churn predictive models for 5-6 different clients.

• DATA SCIENCE INTERN | 09/2015 - 08/2016 | Gainsight Inc | India

• Developed and maintained data pipelines to automate ETL processes..
• Contribute to the building, testing, and deploying predictive machine learning models.
• Qualified for Galvanize BootCamp in Data Science.