Data Scientist · AI/ML Engineer · Data Analyst
I build machine learning systems and data products that turn complex data into practical decisions. I recently graduated with an MS in Data Science from Indiana University Bloomington with 4.0 GPA and bring 1+ years of industry experience across forecasting, pricing analytics, scalable data pipelines, and business intelligence.
My current interests include applied AI, transformer models, time-series forecasting, and machine learning for genomics and healthcare.
- Built production-oriented analytics and ML workflows using Python, SQL, Snowflake, and Azure Data Factory
- Improved enterprise analytical query performance by 60% through optimized ETL pipelines
- Developed demand forecasting models that reduced error by up to 30% over baseline methods
- Built pricing, assortment, and simulation solutions for large retail and CPG datasets
- Developed transformer-based genomic embedding and anomaly-detection workflows in academic research
A personalized university course recommendation application that combines Chroma vector database, LLMs for reasoning, React, Flask, structured course data, align recommendations with career goals.
An end-to-end wellness prediction system exploring tree-based models, neural networks, MLPs, and LSTMs to estimate stress, mood, and overall wellness from structured health data.
An OCR-to-inference NLP system using the Tobacco3482 dataset, Tesseract, DistilBERT, Flask, and React, with single and batch prediction workflows.
An interactive Power BI solution for analyzing trade flows, tariffs, shipping costs, port congestion, industry exposure, and geopolitical disruption risk through a star-schema model and DAX measures.
- Languages: Python, SQL, R, C++
- Machine learning: Regression, classification, time-series forecasting, neural networks, NLP, transformers, anomaly detection, feature engineering
- Data engineering: ETL pipelines, data modeling, Snowflake, Azure Data Factory, PySpark, REST APIs
- Cloud & databases: AWS, Azure, MongoDB, Neo4j, Hadoop
- Applications & visualization: FastAPI, Flask, React, Power BI, Tableau, Plotly, Matplotlib
-
Data Scientist / Research Assistant — Indiana University Bloomington
Building deep-learning pipelines for genomic sequence representation, predictive modeling, and anomaly detection using DNABERT and Nucleotide Transformer embeddings. -
Data Analyst — MathCo
Developed ETL pipelines, pricing and optimization models, assortment analytics, forecasting workflows, and interactive BI applications for enterprise retail and CPG use cases.
- MS, Data Science — Indiana University Bloomington, GPA: 4.0, 2026
- BTech, Mechanical Engineering — SASTRA University, 2023
I'm actively exploring new-grad and early-career opportunities in data science, AI/ML engineering, and data analytics.