Shubham Tamhane

Data Scientist 2 @ Paychex

About

As a dedicated and ambitious Data Science Master's graduate, I bring a unique blend of academic knowledge and practical experience in various domains. My passion for data-driven decision making and problem-solving has been honed through diverse projects and collaborations. I pride myself on being a team player, always ready to share my insights and learn from others. My experience spans across different sectors, providing me with a broad perspective and the ability to adapt to new challenges. I am proficient in various data analysis tools and programming languages, which I have utilized in my academic and professional pursuits. I am a lifelong learner, always excited to explore new technologies and methodologies in the data science field. I am eager to apply my skills in a dynamic team, where I can contribute to solving complex problems and continue my growth. I am open to opportunities where I can make a significant impact with my data science skills. Let's connect!

Country

City

United States

Industry

Computer Software

Skill

Big Data, Computer Vision, Electronic Health Records (EHR), Dashboards, DAX, R, Microsoft SQL Server, Transact-SQL (T-SQL), Meta-analysis, Snowflake, Apache Airflow, Amazon S3, Statistics, Probability, Cloud Computing, Amazon EC2, Azure Databricks, Amazon Web Services (AWS), DevOps, Microsoft Azure

Experience

Data Scientist 2

Paychex

2025-11 - Present · 11 mos

Rochester, New York, United States

Data Scientist

Indiana University School of Public Health-Bloomington

2024-3 - 2025-11 · 1 yr 9 mos

-- Incorporated Microsoft SQL Server in combination with Python for in-depth analysis of healthcare datasets, exceeding 50M records, to derive insights from Electronic Health Record (EHR) data. -- Leveraged T-SQL to clean and preprocess extensive healthcare datasets for a study on patient outcomes, which was conducted in compliance with HIPAA regulations. -- Performed analysis to assess disease diagnosis over 10 years of clinical data, integrating demographic and treatment variables -- Conducted a meta-analysis of over 25 studies and visualized the findings using forest plots to summarize review results

Machine Learning Engineer

Zalliant

2023-9 - 2023-12 · 4 mos

• Developed an ETL pipeline to process real-time multi-sensor data with a 5-millisecond frequency, performing data transformations and loading it from Firehose into AWS S3 for further analysis. • Wrote SQL queries for extracting, aggregating, and analyzing sensor data stored in AWS S3 for downstream model analysis. • Implemented Random Forest as a MultiOutputClassifier in AWS Sagemaker, achieving a 97% accuracy and 92.43% F1 score by extracting time and frequency domain features for behavior classification. • Engineered optimization strategies for data collection frequencies, reducing data volume by 99.6% and extending sensor battery life by 3 months through testing multiple sampling frequencies.

Data Science Intern

Regeneron

2023-6 - 2023-12 · 7 mos

-- Orchestrated ETL pipelines for time series forecasting on a quarterly interval for a inventory management system stored in Redshift with 30,000+ products -- Employed a python-dash application invoking MLOps workflow to provide real-time estimations, customer analysis and model maintenance options to end users and stakeholders. -- Implemented ARIMA and ETS family of models for their clear interpretability, achieving 80% forecasting accuracy, thereby reducing material waste by 30% each quarter. -- Designed interactive dashboards thus optimizing workflows and reducing task turnaround time for end users by 20%. -- Investigated predictive maintenance techniques to estimate Remaining Useful Life (RUL) of Mass Flow Controllers.