Juhi Kamdar | Software Developer

Hi, I'm Juhi Kamdar.

A

Self-driven, quick starter, passionate programmer with a curious mind who enjoys solving a complex and challenging real-world problems.

About

A coder, a writer and a life long learner. Open to learn about travel, politics, psychology and my most favorite Science! Specialized to deal with Computer science I love Deep Learning, have started to develop interest in software engineering. I am in awe of Reinforcement Learning and planning to start soon. I am open to all kinds of opportunities that help me develop professionally. Open source project contributor, Peer reviewer, technical advisor or a freelance consultant. I would gladly help the computer science community to grow. Currently, I am also seeking opportuniies to research in Deep Learning. Feel free to reach out to me if your lab/organization has an opening.

Experience

GMU

Graduate Teaching Assistant

I TA'ed for CS 100 Basics of Computing and CS 583 Analysis of Algorithms

Aug 2022 - May 2023 | Fairfax, Virginia, India

Palo Alto Networks

Software Engineering Intern

Integrated and tested Apigee for API monetization for current API on staging pipeline as a POC. Approximated to generate revenue from API calls with easy analysis, secure connections on top of the existing system.

May 2022 - Aug 2022 | Remote, Fairfax, VA

Tata Consultancy Services

Assistant Systems Engineer

Developed DotNet Applications in C# using MVC Agile principles including database connections while learning to write secure codes with minimal code duplication and strongly structured.
Tools: C#, .Net

Feb 2021 - Jul 2021 | Ahmedabad, India

Indian Institute of Technology-Bombay

Research and Development Intern

Researched, and developed solutions for Attention-based Optical Character Recognition for handwritten forms. Conquering the challenges of background text, boxes in the form, etc we achieved about 80% accuracy.
Researched and experimented on models for knowledge tracing from students’ test papers using Transformer based models. The aim was to understand the actual learning of students based on test answers rather than correctness.
Tools: Python, Scikit-learn, NLTK, pytorch

Sep 2020 - Mar 2021 | Remote, India

Encubate Tech Pvt. Ltd.

Tech Development Intern

Determined requirements, designed, developed, and tested NLP-based search engine. This helped save the cost of using a third-party search engine.
Designed the database schema for it, and prepared a script for automatic code updation to AWS
Tools: Python, Scikit-learn, NLTK, pytorch,

Oct 2020 - Dec 2020 | Remote, India

Indian Institute of Management - Ahmedabad

Research Intern

Researched on Sentiment classification and Emotion Analysis. Preprocessed and cleaned raw Youtube Video Transcripts including use of regex and fine-tuned BERT on the Youtube Video transcripts.
Tools: Python, Huggingface, Seaborn

Jun 2020 - Jul 2020 | Remote, India

SAC, Indian Space Research Organization

Research Intern

Reviewed and researched prevalent cyclone estimation techniques. Experimented with various regression techniques after data processing. The aim of this experiment was to beat a well established statistical method with Machine Learning. Derived results that were almost aligned with those of the statistical method.
Tools: Python, Pandas, ScikitLearn

Dec 2019 - May 2020 | Ahmedabad, India

Projects

                
Music Player Web-App
                  A music streaming web app based on Django
                
AccomplishmentsTools: Django, HTML, CSS, Bootstrap, SQLite, AWS S3, Heroku
Register/login to the web app(with OAuth-based Google Sign-In).
Search and filter songs based on language and singer.
Create multiple playlists and add/remove songs to/from playlist.
Scroll through recently played/viewed songs.

Quiz Web-App
                  A quiz playing web app based on Django
                
AccomplishmentsTools: Django, HTML, CSS, Bootstrap, SQLite, Heroku
Register/login to the web app(with OAuth-based Google Sign-In).
Play Quiz and see the leaderboard

Blog Web-App
                  A simple and extensible blog web-app based on Flask.
                
AccomplishmentsTools: HTML, CSS, Bootstrap, Flask, SQLAlchemy, Postgresql, Python
Users can view posts and contact the admin via Contact Page.
Admin can Add, Delete, Update posts.

Visual Question Answering
                  An attention-based classification model that aims at generating an answer for a given input image.
                
AccomplishmentsIncorporated Convolution Neural Networks (CNN) for extracting image features and Long Short Term
                    Memory for extracting question
                    embeddings.
Tested the model on the COCO dataset, abstract scenes images, and got 69% overall accuracy on the
                    VQA evaluation metric.

Video Summarizer
                  A Seq2Seq model that generates a short summary of the given input video.
                
AccomplishmentsIncorporated CNN to detect and classify objects in the video frames and Long Short Term Memory for
                    generating a summary.
Evaluated the model on MSVD (Microsoft Video Description Corpus) dataset; achieved 0.77, 0.71,
                    0.52 scores respectively on ROGUE,
                    BLEU, METEOR evaluation metrics.

Image Generator
                  An image generator based on the concept of adversarial networks (GANs)
                
AccomplishmentsDeveloped system was tested on a human-face database and loss was calculated by comparing the PCAs
                    of generated and original image.
Calculated difference in PCA was less than 10%, depicting the successful generation of an image by
                    the generator.

Head Counting System
                  A system that calculates the attendance of the class from a panoramic image of a live classroom.
                
AccomplishmentsUsed Singular Value Decomposition for image compression; applied various image processing
                    techniques and morphological operations to
                    detect the number of heads.