Hi, I’m Sargun!
I am a Master’s in Data Science student at the NYU Center for Data Science and bring 3+ years of hands-on experience specializing in Machine Learning and NLP. As a Data Science Intern at Marsh McLennan (NY), I led the development of an impactful industry benchmarking pipeline, leveraging LLMs, Clustering, and Hypothesis Testing, showcasing my ability to translate raw data into actionable insights for business stakeholders.
Preceding my Master’s, I spent 2 years as a Data Scientist at Fidelity Investments, pioneering data products that saved time and money for financial advisors and analysts. My contributions spanned Document Information Extraction, Text Summarization, and Email Fraud Detection.
I love working on data for social good projects and as a Research Engineer, I published research papers on Statistics and ML for COVID-19 caseload prediction and devising interventions to mitigate infection outbreaks.
Featured Projects
Fine-tuned 7B parameter LLMs (LLaMa), BERT-based models (XLM-R), and zero-shot LLM Prompting for Hindi-English hate speech detection.
Trained multi-modal text-vision models for detecting previously unseen objects in video frames based on natural language queries.
Statistical analysis of job data (Hypothesis Testing), Salary Prediction (Regression), and Job Title Prediction (Classification).
Novel method of using Language Models and Machine Learning to predict COVID-19 cases and emerging variants.