
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Data Scientist II @ Amazon | Artificial Intelligence (AI), Machine Learning, Fraud Detection, Data Infrastructure
Results-driven Data Scientist with Master’s degree in Data Science specialization and 10+ years of experience in Artificial Intelligence, Machine Learning, fraud detection, and building scalable data infrastructure. Delivered $50M+ savings in fraud prevention through innovative solutions including patent-pending causal inference system for multi-account fraud network detection (77% accuracy, 40% abuse collapse rate) and advanced clustering algorithms. Expert in building end-to-end ML pipelines from data engineering to production deployment across AWS, Spark, and Python ecosystems. Proven track record in developing agentic AI systems, real-time analytics platforms, and enterprise-scale data lakes while leading cross-functional teams. Strong background in translating complex business requirements into production-ready solutions that drive measurable business impact and operational excellence.
Northeastern University
Master of Science (MS), Information Systems
January 1, 2016 – January 1, 2018
R. C. Patel Institute of Technology, Shirpur
Bachelor of Engineering (B.E.), Computer Engineering
January 1, 2009 – January 1, 2013
Amazon
Data Scientist II
April 1, 2024 – Present
Seattle, Washington, United States
Amazon
Data Engineer II
August 1, 2020 – April 1, 2024
Seattle, Washington, United States
DraftKings Inc.
Senior Data Engineer
March 1, 2020 – August 1, 2020
DraftKings Inc.
Data Engineer
August 1, 2018 – March 1, 2020
Dassault Systèmes
Machine Learning Engineer Intern, R&D
May 1, 2017 – November 1, 2017
Greater Boston
Accenture
ETL Data Engineer
November 1, 2013 – July 1, 2016
Mumbai
User Registration App (Amazon Web Services)
October 1, 2017 – December 1, 2017
• Built Spring Boot Application using REST API & deployed it on AWS using CodeDeploy and TravisCI • Created AWS Services like EC2, S3, RDS, DynamoDB, IAM and SNS using CloudFormation
Live Internet Blog Analysis : Machine Learning & NLP
April 1, 2017 – Present
• Collected all live blogs and classified them as relevant or not using Neural Networks, Random Forest and Logistic Regression on user’s keyword • Trained the model using TF-IDF and clustered using Gensim – LDA to respective categories • Pipelined entire flow using Luigi, visualized different categories using t-SNE - DR Algorithm and Tableau
Lending Club - Machine Learning
March 1, 2017 – April 1, 2017
• Automated and scheduled the entire process using Luigi Workflow and Docker • Created a Web UI using C# and asp, which takes input from users, calculate the credit score and predicts the interest rate based on the credit history of the user • Implemented Random Forest, Logistic, KNN, K-Means and Neural Networks on the data and the model with the best accuracy is implemented in Azure Machine Learning Studio and deployed the web service using Rest API
Boston Housing and Loan Dataset: Machine Learning
March 1, 2017 – Present
Scraped a very large dataset of Boston Housing provided by freddiemac.com from the year 1999 to 2016 Pre-processed the data based on various anomalies and null values using various Python Libraries and dockerized the whole process Implemented various Machine Learning Algorithms like Logistics, Random Forest, SVM, KNN and Neural Networks on one quarter data to predict the interest rate of housing loans on the next quarter data and showcased various analysis and trends using Tableau
Titanic: Machine Learning from Disaster
January 1, 2017 – Present
Completed this Kaggle Competition in Machine Leaning by exploring the datasets provided by Kaggle. Predicted the survival rate of the people by feature engineering the data set using R and Random Forests Algorithm. The prediction of Survival Rate using my method yielded 81.59% accuracy, which is among the top 5% of all time Leader Boards for the Competition involving more than 6100 teams.
IMDB Database
November 1, 2016 – Present
Created an IMDB database in Relational Databases like SQL Server and Oracle and Non-Relational Database like Hive. Created ER model normalized up to 3rd Normal Form and covering various additional features of IMDB using Stored Procedure, Functions and Triggers. The remarkable feature was the statistical and analytical data shown using Tableau.
BeingHuman System
November 1, 2016 – Present
Developed a system as a One Stop Shop for all the social activities like Blood Donation, emergency blood requirement, food wastage and plastic conservation system using Ecosystem model. Some exceptional features were the use of Geolocation, Barcode Generator, Email notifications, encrypting and storing password of the users using one-way hashing technique and the analysis of the social work done using multiple pie-charts.
Metric Logs Automation
June 1, 2015 – August 1, 2015
Automated the metrics log with the help of Unix Shell scripting and HTML tags to make it visually good. Also used Qlikview to show the trends of the metrics log of the project over the years.
Mobi Travel Guide - Android Application
March 1, 2013 – June 1, 2013
Developed an Android application to help tourists visiting new places to manage famous spots on their own without the help of any guide. The remarkable feature was the use of Data Analytics to show the trend and evolution of the tourist place over the last few years.
Automatic Number Plate Recognition
February 1, 2012 – April 1, 2012
Developed a surveillance system using Optical Character Recognition (OCR) to read vehicle's registration plate. We increased the number of frames per second so that it could capture the text in the plate at the speed of 25 kmph for recognizing a vehicle's number plate.
AWS Certified Solutions Architect – Associate
Amazon Web Services (AWS)
June 24, 2026 – Present
Data Mining Engineering
Northeastern University
June 24, 2026 – Present
Cultural Fit Analysis
The candidate's diverse project portfolio, ranging from machine learning and NLP to full-stack development and Android applications, indicates a broad interest and adaptability. Their experience in large, fast-paced environments like Amazon and DraftKings suggests a good fit for a dynamic, results-oriented culture. The progression from Data Engineer to Senior Data Engineer and Data Scientist II shows a commitment to growth and continuous learning, which aligns with a strong cultural fit.
Soft Skills & Operational Fit
The candidate's experience at Amazon and DraftKings, including leading teams and managing complex data migrations, suggests strong operational fit and leadership potential. The project descriptions indicate a proactive approach to problem-solving and automation. However, without specific psychometric or English test scores, a detailed assessment of soft skills like logical reasoning, work attitude, stress handling, and team collaboration is limited.