Vikas Raunak

Vikas Raunak

Software Engineer at Microsoft

B.Tech (Gold Medallist), IIT Indore

Image Generated with Neural Style Transfer using a Cubist Image.

About Me

Hi, my name is Vikas Raunak. I am orginally from Madhubani (in Bihar, India), which is quite famous for its paintings. I did my B.Tech. in computer science and engineering at Indian Institute of Technology, Indore. My interest in computer science initially developed by trying to understand how the Internet works. After making a few web and mobile applications, I worked on Multipath TCP as my B.Tech Project, where I implemented & improved upon the key algorithms within the protocol and learnt the complexities of algorithm design in general. However, after reading the paper on TCP Ex Machina, I became more than convinced that learning algorithms from data is the right way to approach several problems and hand crafted algorithms can only take us so far. Incidentally, a lot of people already had similar thoughts (pragmatically coping with a problem can provide a satisfactory solution in the absence of any theory of the problem. ), much much before I had them :).

Recently, at Microsoft, I built a tool for analysing telemetry data, originating from web applications and services. The tool models several practical problems of interest (e.g. Identifying top workflows, Behavior based anomaly detection, Identifying top deployment slots, etc.) in terms of machine learning techniques such as Topic Modeling, Time Series Decomposition, Streaming Least Squares etc. At Microsoft, I also won four Hackathons (at different levels: Global, India, Org & Campus Hires) with different teams, for building ML powered software systems. I also developed an algorithm that reduces word embedding dimensionality by 50% while preserving its performance. The work was accepted for poster presentation at NIPS LLLD Workshop.

Key Projects

project name

Real Time Twitter Sentiment Visualization AI

Supervised by: Dr. Aruna Tiwari

The project involved building a web application capable of computing the sentiment scores of a stream of Tweets in real-time and visualizing the sentiment on the world map. Mainly used JavaScript and Node.js platform for creating the application. For streaming, we used Twitter Firehose and the visualization was done on Google Maps (using Heat map + markers). The algorithm employed was the Naive Bayes classifier algorithm (combined with the dictionary based approach).

project name

REST API based Web and Android app DBMS

Supervised by: Dr. Somnath Dey

The project involved creating a web application (a collaborative Note-taking application) and an android app that would communicate with a central MySQL database through an API based on the REST architectural pattern. Created the REST API in PHP using the Slim framework. Used Retrofit library in the Android app. Also implemented search, update and comment functionalities.

project name

Institute Alumni Website Software Engineering

Supervised by: Dr. Abhishek Srivastava

Designed, developed and tested the Institute Alumni website plus social network. Used Bootstrap, JavaScript/JQuery for the front-end and PHP for the backend. Implemented several features such as friend request, mass mails, approval system, polls, blog, picture Gallery etc.

View on Github

project name

Object Detection in Image Processing Algorithm Design

Supervised by: Dr. Kapil Ahuja

The project involved building a software that could count the number of objects in a black and white image. This involved pre-processing of the image for noise reduction and then, the application of image segmentation and graph algorithms. The project was implemented in MATLAB.

Previous Work Experience

Microsoft India (R&D) Pvt. Ltd. - Hyderabad (May - July 2015) Internship

Worked as SDE Intern (Internal Tools division) on Product Activation services development and test automation. Created OData based endpoints using Entity Framework and automated the testing process by creating a Test Automation Suite. Worked with Git throughout the project and finally, my code went went into production.

Other Projects

Rendering Motion-Blur Effect in Real-Time Computer Graphics

Supervised by: Dr. Somnath Dey

Implemented C++ program (using OpenGL) to render (simulate) motion blur effect in moving objects by blending images.

Image Registration Using Firefly Algorithm Optimization Algorithms

Supervised by: Dr. Kapil Ahuja

Used the firefly optimization algorithm to solve the problem of image registration. Implemented the program in MATLAB.

Character Recognition Using Clustering Machine Learning

Supervised by: Dr. Surya Prakash

Used K-Means clustering algorithm to group poorly drawn alphabets. Implemented the program in MATLAB.

Humanities Projects

Policy Response to the Great Recession International Economics

Supervised by: Dr. Ruchi Sharma

Analyzed the nature of and policy response to the 2007-08 Recession through numerous case studies.

Find out more

Citizenship in the Twenty-First Century English Language Lab

Supervised by: Dr. Nirmala Menon

Explored the ideals and practice of, as well as challenges to the notion of citizenship in the modern world.

My GitHub Activity