Jun 2022 – Sep 2022 · 3 mos

• Research Intern at Microsoft Research Semantic Machines

Sep 2021 – Mar 2025 · 3 yrs 6 mos

Mar 2021 – Jun 2021 · 3 mos

• CSE 151A: Introduction to Machine Learning

Jan 2021 – Mar 2021 · 2 mos

• DSC 190: Introduction to Data Mining

Oct 2020 – Dec 2020 · 2 mos

• CSE 291: Advanced Data-Driven Text Mining

Aug 2020 – Sep 2020 · 1 mo

• CSE 21: Mathematics for Algorithms and Systems Analysis

Mar 2020 – Jun 2020 · 3 mos

• DSC 190: Introduction to Data Mining

Jan 2020 – Mar 2020 · 2 mos

• CSE 8B: Introduction to Programming in Java.

Sep 2019 – Jun 2021 · 1 yr 9 mos

• META: Metadata-Empowered Weak Supervision for Text Classification | Advisor: Prof. Jingbo Shang
• Proposed a novel framework that leverages metadata information as an additional source of weak supervision and incorporated it into the classification framework.
• Our method organizes the text data and metadata together into a text-rich network and employs motif-patterns to capture appropriate metadata combinations.
• Using the seed words and motif patterns, our method generates pseudo labels, trains classifier, and ranks and filters highly label-indicative words, motifs in a unified manner and adds them to their respective seed set.
• Contextualized Weakly Supervised Text Classification | Advisor: Prof. Jingbo Shang
• Proposed a novel framework that performs contextualized weakly supervised text classification.
• Our framework contextualizes corpus and identifies the interpretation of seed words, classifies the documents and expand the seed words in an iterative fashion.
• To the best of our knowledge, this is the first work on contextualized weak supervision for text classification.

Jun 2021 – Sep 2021 · 3 mos · Seattle, Washington, United States

• Product Graph team

Apr 2018 – Jul 2019 · 1 yr 3 mos

• Architected and built Sprinklr AI's visual insights module.
• Object Localization - Developed in-house computer vision models for visual sentiment, gender, age, inappropriate content detection in images and videos.
• Font Recognition - Built in-house computer vision model that identifies the font and suggests similar fonts from an image.
• Auto Scaling Framework - Developed a dockerized auto-scaling python-based framework which is deployed in kubernetes for image classification. It works over a stream of data published to Kafka and thus is auto-scaled based on lag in Kafka queue. Integrated the machine learning framework with Sprinklr platform and it is now used to serve over 1200 Sprinklr clients.
• Scalability – Developed a scalable system capable of running classification models over 500 million messages per day using the latest technologies like Caffe, Tensorflow, Kafka and Elasticsearch.
• Monitoring – Deployed a centralized monitoring environment(Grafana, InfluxDB, CollectD) which gather system metrics as well as docker run-time metrics.
• Implementation - Implementation was done using asynchronous programming and as a result, throughput was increased by 65% and total resources cost reduced by 50%.

Jul 2017 – Apr 2018 · 9 mos

• Backend Development in Paid Advertising Module.
• Implemented an end to end pipeline that incorporates DoubleClick tracking in ads for integrated reporting.
• Expanded the reach of the product by integrating Ads APIs of various social media channels like LinkedIn, Twitter, Google DCM.
• Researched, Designed and Implemented core functionalities in backend code to improve the feature of importing and exporting ads which is the primary way, the users undergo to create ads.

May 2016 – Jul 2016 · 2 mos · Bangalore

• Auto-Routing cases in Microsoft Dynamics CRM.
• Developed machine learning models in Microsoft Azure Machine Learning studio which predicts the ideal assignment candidate for a case.
• Designed and deployed a web service which periodically retrieves case data from CRM and re-trains machine learning model.
• Created solution that exposes options to use above features via GUI in Microsoft Dynamics CRM.
• Built a robust pipeline which connects Microsoft Dynamics CRM and Azure ML studio.

Dec 2015 – Dec 2015 · 0 mo · Hyderabad Area, India

• Efficient Vehicle Tracking.
• Designed and implemented an algorithm to speed up search queries related to the location of the vehicle, from 120 seconds to 5 seconds.
• Designed an algorithm that dynamically analyses accelerometer data of a moving vehicle to identify outliers and driving style of the driver.

Jul 2014 – Jul 2015 · 1 yr · Kanpur Area, India

• • Mentored a group of six freshmen and ensured their smooth transition into the campus through academic guidance and counseling.

Jul 2014 – Jul 2015 · 1 yr · Kanpur Area, India

• • Mentored freshmen for the course Fundamentals of Computing.