Hi, this is Rutvik

I'm a |

I’m Rutvik, a Data Scientist with a background in Statistics and real-world AI and ML experience across e-commerce, insurance, and manufacturing. I’m passionate about working with data that actually drives decisions and improves user or business outcomes statistically. My interests lie in building AI-powered tools, automating repetitive tasks, and creating systems that save people time. Outside of work, you’ll usually find me watching sports or playing a good game of cards.

Skills

Python
PyTorch
Scikit-learn
SQL
AWS
Streamlit
React
GitHub
Pandas
Matplotlib
NumPy
NumPy

Work Experience

Amazon

Data Scientist - Bangalore, IN | Jan 2022 – Aug 2023

  • Development of scalable NER-MQMRC architectures across 19 marketplaces.
  • Unit of measurement mismatch resolution across 2 million product families.
  • Research on LLMs to enhance image-based data.
  • Sentiment Analysis for Attribute Extraction.
  • Designed an anomaly detection workflow to increase precision by 4% across 800,000 products.

Northeastern University

Graduate Teaching Assistant — Unsupervised ML - Boston, MA | Jan 2025 – Apr 2025

  • Mentored 80+ graduate students by addressing Mathematics and Python programming challenges related to Unsupervised Machine Learning topics such as PCA, t-SNE clustering, and Latent Dirichlet Allocation.
  • Presented effective in-person code demonstrations on clustering techniques, EM algorithms, and knowledge-based QA graphs.

Veeco Instruments

Data Scientist Co-Op — San Jose, CA | Jun 2024 – Dec 2024

  • Engineered a Python-based executable application for data visualization of Gaussian statistics and beam profile metrics, reducing report consolidation time by over 75% compared to the previous MATLAB workflow.
  • Invented and programmed a circular Convolutional Neural Network to model resistance uniformity in Boron wafers, reducing manufacturing errors to 5% and saving $1,200 per wafer in costs.
  • Designed and incorporated a parallel batch processing system in Python to analyze 30+ data files, validating the impact of lamp shutter timing on peak variability in Laser Spike Annealing (LSA) signals.

Tata AIG General Insurance Company

Data Analyst Intern — Mumbai, IN | May 2021 – Jun 2021

  • Reduced insurance fleet premiums by 2.5% using time-series forecasting with Vector Auto-Regression (VAR) models.
  • Ideated a Pay-as-You-Drive scheme to introduce variable premiums based on miles driven.

Projects

CodeSynth: AI Agent for Statistical Modeling

An AI-powered assistant that generates Python code for data analysis tasks using LangGraph and Streamlit.

Tools: Python, LangGraph, Streamlit, OpenAI, Llama, Gemini

Recommendation System using DeepCoNN

A deep learning-based recommendation system using user reviews to predict ratings and rank relevant products.

Tools: PyTorch, Python, Streamlit

ColdEmail Generator

A web application that generates and sends personalized cold emails to recruiters and managers without opening Gmail or Outlook. It customizes email content based on job descriptions by leveraging an AI agent through API calls.

Tools: React.js, API Integration, Fine-Tuning AI, Prompt Engineering

Autoencoder Analysis on Image Data

Explored feature extraction using autoencoders for image classification and reconstruction. Compared standalone and composite models, with the composite model achieving superior performance.

Tools: Python, Scikit-learn, Autoencoders, Supervised Learning

The Delivery Cube

Designed and implemented a relational database system for a food and grocery delivery service. Built 10+ tables and applied DDL, DML, and DQL operations to manage customers, orders, deliveries, and inventory efficiently.

Tools: SQL

Measuring Financial Risk Using Extreme Value Theory

Analyzed financial market data using Gumbel and Pareto distributions to estimate Value-at-Risk (VaR) and Expected Shortfall (ES) at the 2% level.

Tools: Python, Extreme Value Theory, Financial Risk Metrics

Education

Northeastern University

Master of Science in Data Science | Boston, MA | Sep 2023 – Present

GPA: 4.0 / 4.0

  • Served as a Graduate TA for Unsupervised Machine Learning
  • Worked on multiple academic projects and implemented key ML algorithms
  • Participated in Intramurals and led the team to Semi-Finals in 2 semesters

NMIMS University

Master of Science in Applied Statistics and Analytics | Mumbai, IN | Jul 2020 – May 2022

GPA: 3.73 / 4.0

  • Served as Class Representative for 2 consecutive years.
  • Led 2 major academic projects and secured 5th place in a university-wide hackathon.
  • Organized and hosted multiple quizzes and social events.

Savitribai Phule Pune University

Bachelor of Science in Statistics | Pune, IN | Jun 2017 – Apr 2020

GPA: 3.71 / 4.0

  • Secured Class Rank 2 among peers.
  • Participated in the Statathon competition hosted by the university.

Contact Me