Since September 2019, I have been working with Machine Learning Team at Fynd as a Machine Learning Engineer, where I have been repeatedly recognized for developing innovative solutions for great software applications based on Deep Neural Networks and solving a wide range of problems.
Here, I am responsible for full lifecycle development of next-generation software, from initial data collection and analysis to designing Deep Neural Networks and deployment on Edge.
Maharaja Agrasen Institute of Technology, Delhi
B.Tech(CSE) 2015 - 2019
CGPA: 8.3 / 10.0
Fynd is India’s largest offline to online (O2O) co works with retailers to enable their store inventory to be shoppable across different online and offline channels beyond the store. Online customers can buy these products on the Fynd Apps, Fynd.com, the brand’s own website, prominent market places like Amazon, Myntra, TataCliq and Google.
Great! place to learn.
Completed six-week independent solo project to detect facial keypoint. This involved data collection and preparation, designing a deep neural network and finally deployment on Android. Bash was used for data preparation. The data was converted to TFRecord format for efficient use of tf data pipelines.
Worked as a member of cross-functional four-person team for GlamAR which offer users the ability to try virtual makeup. I was responsible for writting the computer vision algorithms in c++.
Completed three-week independent solo project to acheive a decent FPS for segmentation tasks on Mobile Devices. This involved data preparation, implementing DNNs described in relevant research papers with some modificiation and deployment on Android. Achieved 10+ FPS on low end devices and 20+ FPS on high end devices.
Successfully completed a POC on tracking multiple objects with the help of two cameras
I worked on this project during my undergrad to explore the fundamentals of AI. This is directly inspired from Pac Man. The project is written using C++. The source code is availabe at github .
During my undergrad, Internet Relay Chat was a main platform for discussion on various topics. The protocol is such that it disconnects you automatically if you remain inactive for a certain period of time. Thats when I decided to write a basic IRC client for me. I have Followed the IRC protocol descrbed in RFC-1459. The source code is available at github.