Vivek Tiwari

About Me

My name is Vivek and i am a graduate student at University of Southern California currently working as Software Intern @ Samsung Research (SSIC). Prior to graduate school, i have three years of working experience in designing enterprise application for fortune 100 companies. During the course of my work i have handled multiple hats where my roles and responsibilities ranged over team lead, scrum master, etc. I believe my greatest strength includes my ability to communicate openly and out of box thinking. I tend to do things differently but in an efficient manner. To be more specific I want to work in those domains that creates huge impact on the life of the people for a good well being.

Contact Details

Vivek Tiwari
SAL 104 Mail Code: 0781
Los Angeles, CA 90089-0781
United States of America


University of Southern California

Master's in Computer Science

CourseLoad: Analysis of Algorithms,Artifical Intelligence, Natural Language Processing, Database Systems, Information retrival, Artificial Intelligence for social good.

Graphic Era University

B-Tech in Computer Science

CourseLoad: Data Structures, Web technologies, Database Systems, Engineering Mathematics


Samsung Research (SSIC)

Software Developer Intern May 2017 - Currently

•  Involved in designed and development of IoT cloud (
•  Address performance improvements to existing front end application stack.

University of Southern California

Software Developer-Team core Research Group June 2016 - May 2017

•   Build a classifier which predicts the location of mouse click in real time based on User mouse movement.
•   Developing algorithms for sequential planning under uncertainty in multi agent systems.
•   Emphasis on influence maximization in real-world social network domain

Infosys Technologies Ltd.

Senior System Engineer July 2012 - October 2015

•  Designed and developed MVC Framework for Ricoh that decreased development cycle by 50 percent. I was responsible for designing WebSql schema to provide offline data storage, localization, Centralized handling of error and warning messages.

•  Implemented “Add to cart Functionality” for one of the biggest US E-commerce Retailer. My responsibilities include integrating the existing UI into the framework and implement the add to card functionality in java

•  Developed MVC components for the Hybrid Enterprise web application. Developed custom plugins to read and write data from the Web server in the pdf format.

•  Design and develop 3D 9*9*9 cube for one of the world largest Oil Field Service company. The application is mainly used for data analysis using slicing and dicing technique.

Infosys Technologies Ltd.

Winter Internship Jan 2012 - May 2012

•  Designed and developed android based “Free hand drawing application: SketchDroid”. I am responsible for designing the algorithm that supports canvas, touch screen gesture features in mobile devices.

HCL Technologies Ltd.

Summer Internship Jun 2011 - July 2011

•  Designed and developed Incident reporting management portal(IRMS) using PostgreSQL that helps employees to keep track of all the incidents that are resolved or are in open state. Furthermore, it helped HCL to increase the learning curve of their employees about an incident by 42%


Influence Diagram (Bayes Net)

April 2016

Given a set of nodes (Chance node, Decision node, etc.) in a file, build a Bayesian network and then compute probability, expected utility and Maximum Expected utility in the network using Variable Enumeration Algorithm.

Building an Apache-Solr based Search Engine, Ranking Algorithms

April 2017

Developed an indexing system using Apache Solr and lucene that allows user to search for content, answer queries on Gutenberg dataset.Uesr interact with webpage that allow to insert queries. These queries are then send to the middleware that parse query, extract keywords and send to solr server. Solr process these queries, fetch posting list and then send back results to the user.

Sequence Labeling using Conditional Random Field

November 2016

Assigning dialogue acts to sequences of utterances in conversations from SWBD(SwitchBoard) DAMSL using CRF suite and hence generate a set of baseline and advanced features

Chatbot : Artificial Intelligence chat assistance for shopping

December 2016

Chatbot employ a conversational UI, enabling users to easily jump to any point in the task flow, unlike conventional mobile apps, which tend to progress in one direction through a predefined set of screens. By understanding user intent and saving proper context, this application can effortlessly jump forward and backward multiple steps at a time, with little overhead.

Implement Perceptron (Neural Networks)

October 2016

Implemented simple but effective machine learning model, the perceptron, and applying it to a binary text classification task (i.e., spam detection). Implemented both standard and averaged perceptron model on the corpus containing 44000 E-mail data and then to classify dev data consisting of 22000 mail records. and to Calculated the Average, Precision and F-score on actual result.

Maximizing the spread of sexual health information in a multimodal communication network of young Black women

January 2017

Analyze results of a Los Angeles-based network of 73 YBW’s multimodal communication behaviors, with a particular focus on (a) how information about sexuality and sexual health was spread among this network, and via which communication modes; (b) how we leveraged this network data to simulate and model how to optimize information flow within different communication modalities in a hypothetical peer leader intervention program; and (c) how different modalities of peer leaders impact the spread of information, and which optimal individuals should be selected to maximize this spread.

Inference Engine

Feb 2016

Project involved constructing a knowledge base from First Order Logic Clauses. The inference engine uses backward chaining algorithm to infer and answer the logical queries posed to the system and the logs in order of which queries are processed.

Responsive Web Application for Searching Congress Database

June 2016

Built an interface to perform congress database search using SunLight API. Display the congress information and add and remove Congressmen, bills and committees to favorite list (Bookmark - implemented using Locastorage).Filter the search for any information inside the application itself, to view specific Bill, Committee and Congressmen.

Creating, Visualizing and Querying Spatial Data

June 2016

Worked with spatial data to create some data, visualize it, and then do queries on it, and visualize the query results. Got lat longs of points of interest and created a KML file. Visualized the KML file using Google Earth. Used Quantum GIS (QGIS) to convert the KML files to shape files. Visualized the shape files using ArcGIS Explorer. Used Postgres+PostGIS to find the convex hull of the points and 3 nearest neighbors to a point of interest. Created a Spirograph around a point of interest using a python script and then visualizing the results on Google Earth

Symbiotic Relationship between R and Weka

June 2016

Created four set of clusters consisting of 100 points each in R language. Visualize each cluster within a unit square in R console and generate .arff format file. Use .arff file to generate cluster using SimpleKmeans algorithm and to visualize the clusters in WEKA tool.

Data Analysis Using Hadoop & Map Reduce

June 2016

Analyze logs from the web server and to implement MapReduce jobs on multiple clusters to identify ip address, pages that are accessed most. Furthermore, performed ETL, data processing and analytics using R and WEKA to get further insight from the collected data.

Spam Detection using Supervised Learning Algorithm

August 2016

Developed a general multi-class Naive Bayes Classifier and used it to train data obtained from a corpus of 22,000 raw emails contents. Used "bag of words" technique for feature extraction. Applied Tokenized algorithms on the training data to generate training and development modules. Calculated the Average, Precision and F-score on actual result.

Analyze Sales Dataset

June 2016

Developed mapper and reducers for distributed multi cluster system of sales logs collected from OLAP systems to analyze sales trends and further categorized sales based on various metrics such as location, product category, etc.

Enhancing search engine with Spellcheck and suggest in Solr

April 2017

Implemented a powerful auto-suggest, spelling correction feature in search application using Solr. Furthermore improve the original Solr auto suggest feature to display the most relevant suggestion fetched from the indexed Gutenberg dataset

Artificial Intelligent Game

Jan 2016

Developed an Artificial Intelligent Agent to play 5*5 Matrix Board Game in python, Agent selects the next move by first plotting a game graph and then selecting the next move using Adversarial search (Minimax search, Alpha Beta Pruning).

Text Editor

Feb 2011

Designed Text Editor using JavaScript that enables end user to perform various operations such as Text Formatting, Find & Replace, Undo and Redo. It also has advanced features like Data Transformation which allow to load and merge content from external file.


Professor Milind Tambe

Vivek has been doing a fantastic job with our research group. We as a research group are thoroughly impressed with his dedication and hardwork, and his skills. He has been extremely responsive to our students' requests and as a result he is popular with everyone in the research group.

Thomas George

Vivek worked on the Visualizing Android OpenGl application for one of the largest oil client. The application is mainly used for visualizing the employee/Sales data using slicing and dicing technique. It is one of the challenging project since it require extensive knowledge of graphics and mobile operating system

Check Out Some of My Works.

Contact Information

SAL 104, Los Angeles, CA 90089, US
Phone: (213)675-3993
Email: vivektiw
Leave a Note?