
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Machine Learning @ Amazon
I’m an Applied Scientist with over seven years of experience leveraging Machine Learning and AI to solve complex business problems. Currently, at Amazon Business, I focus on developing ML-driven solutions for customer acquisition and identification, creating impactful strategies to drive growth. Previously, at Supportiv, I led initiatives in mental health innovation, improving recommendation systems by 20% and pioneering efficient NLP solutions that significantly reduced costs and execution time. At Amazon Alexa Privacy, I developed advanced privacy transformation techniques, safeguarding sensitive data while maintaining high model performance. Earlier at JPMorgan Chase, I utilized AI to streamline operational processes, saving resources and improving efficiency. My expertise spans deep learning, recommendation systems, NLP, and data privacy, with a proven track record of delivering measurable results across diverse industries. I’m passionate about building scalable AI systems that bridge innovation with real-world business impact. Let’s connect to explore how we can tackle challenging problems with cutting-edge technology.
Northeastern University
Master of Science - MS, Computer Science
January 1, 2018 – January 1, 2020
Dwarkadas J. Sanghvi College of Engineering
Bachelor of Engineering (B.E.), Computer Science
January 1, 2012 – January 1, 2016
Amazon
Applied Scientist II
January 1, 2025 – Present
Seattle, Washington, United States · On-site
Supportiv
AI / Machine Learning Engineer
January 1, 2023 – December 1, 2024
Amazon
Applied Scientist
February 1, 2021 – January 1, 2023
Seattle, Washington, United States
JPMorgan Chase & Co.
Machine Learning Engineer
July 1, 2016 – June 1, 2018
Mumbai, Maharashtra, India
Search Engine - Information Retrieval
November 1, 2018 – December 1, 2018
•Developed a search engine with components such as index creation, text transformation, retrieval models and evaluation metrics. • Used Pseudo Relevance feedback for query enrichment and BM25, tf-idf, JM smoothing and Lucene retrieval models. • Built snippet generation using Luhn’s algorithm for sentence significance factor calculation.
Avoiding food wastage
June 1, 2018 – Present
A Django based web platform that plans to serve as a way to avoid wasting food in households and restaurants/ events. It provides a portal for people to make a food donation and a portal for non-profits and other social welfare organizations to view the live donations and accept.
Football Match Winner Prediction
December 1, 2015 – April 1, 2016
• Developed a software to predict the outcome of a match using machine learning. It uses statistical data collected by crawling web pages from a match like shots,form,goals etc. to train the classifiers like Logistic Regression, Random forest and Naive Bayes to predict the outcome. • Tools- Python,Java,PyCharm (IDE).
MEDICAL STORE OPERATIONS SOFTWARE
October 1, 2014 – Present
• Developed a daily business operations software providing inventory management, invoicing, cart, medicine details as well as alternate medicines . User Friendly UI for customer profiles, employee profiles and sales statistics. • Tools used- Java, Sqlite, Netbeans.
Cultural Fit Analysis
The candidate's project portfolio shows a mix of academic and personal projects, including social impact (avoiding food wastage) and core computer science (search engine). Their professional experience is heavily concentrated in AI/ML roles, which aligns with a research-oriented or advanced technical culture. However, the target role is 'Backend Engineer', which is a significant pivot from their primary experience in Applied Scientist/ML Engineer roles. While they have some foundational Java/Python experience from projects, the depth in core backend engineering principles (e.g., distributed systems, API design, database optimization beyond basic SQL, cloud infrastructure) is not explicitly demonstrated, which could be a cultural fit challenge for a pure backend role.
Soft Skills & Operational Fit
The candidate's experience descriptions highlight problem-solving, innovation (pioneered privacy data auditor), and efficiency improvements (reduced expenses, execution time). These indicate a strong operational fit for roles requiring initiative and impact. However, direct assessment of soft skills like teamwork or stress handling is not possible without psychometric test results or interview data.