Hi, I'm Zain.

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


I am a Natural Language Processing Graduate Student at Mohamed bin Zayed University of Artificial Intelligence. I enjoy problem-solving and coding. Always strive to bring 100% to the work I do. I have worked on technologies like Python, Django, Flask, MySQL, PostgreSQL, MongoDB, HTML5, CSS, C++ during my bachelor's. I have 19 months of professional work experience which helped me strengthen my experience in Vue.js, jset, and Django. I am passionate about developing complex applications that solve real-world problems impacting millions of users. I always wish to work and study in a competitive and innovative environment where there are new challenges with every new project so that I can learn and enhance my technical, analytical, and managerial skills. My research interests lie in Deep Learning mainly in the field of natural language processing and end-to-end text-to-speech systems.

  • Languages: Python, JavaScript, C, C++, HTML/CSS, Bash
  • Databases: MySQL, PostgreSQL, MongoDB
  • Libraries: Numpy, Pandas, Librosa, Scikit-Learn, NLTK, OpenCV
  • Frameworks: Flask, Django, Vue.js, Node.js, Selenium, Keras, TensorFlow, PyTorch, Bootstrap
  • Tools & Technologies: Git, Docker, AWS, GCP, Heroku, JIRA

Looking for an opportunity to work in a challenging position combining my skills in Software Engineering, which provides professional development, interesting experiences and personal growth.


Software Engineer
  • Design, code, and debug related to front-end development.
  • Fully automate the UI testing using Selenium framework.
  • Maintain and upgrade existing products to improve their performance.
  • Train other developers and manage the technical aspects of projects.
  • Improved the response time by 20% by refactoring the codebase and changing database design and queries.
  • Tools: Vue.js, Python, Flask, MongoDB
October 2021 - June 2023 | Chatham, New Jersey
Research Officer G-II
  • Research and development of an end-to-end Urdu Text-to-Speech system using deep learning.
  • Full stack development of an automated Urdu broadcast media content extraction and analytics system using Django framework.
  • Development of NLP module to generate phonetic stream from plain Urdu text for the production of natural and intelligible speech.
  • Development of statistical POS tagger for Urdu using different machine learning approaches.
  • Creation of installation package for the deployment of HMM based Urdu SAPI voice in Windows environment.
  • Implementation of Fernet encryption for Urdu lexicon.
  • Tools: Python, Django, Keras, Tensorflow, PyTorch, MySQL
December 2020 - October 2021 | Lahore, Pakistan
Internee Engineer
  • To predict the failure of Power Transformers based on dissolved gas analysis (DGA) data
  • Created an alert system to send notifications and emails when the parameters exceed the threshold.
  • Supervising repair, winding, insulation and testing section of the workshop.
  • Tools: Python, Flask, JavaScript
June 2019 - July 2019 | Lahore, Pakistan


speech emotion recognitions
Speech Emotion Recognition

A CNN, LSTM and Attention based model to recognize human emotions.

  • Tools: Scikit-Learn, Librosa, PyTorch
  • A CNN, LSTM and Attention based model is made using PyTorch.
  • The model is trained using RAVDESS dataset.
  • The algorithm is able to predict a total of 8 emotions with upto 96% accuracy.
sentiment analysis
Sentiment Analysis Deployment

An RNN based deployed model for sentiment analysis using AWS.

  • Tools: Pickle, Scikit-Learn, NLTK, PyTorch, AWS Sagemaker, AWS Lambda, EC2, API Gateway, Endpoints
  • Designed an RNN in PyTorch and trained this model on movie reviews from IMDB.
  • Deployed its web application as user interface using AWS.
Face generation
Face Generation

A deep convolutional generative adversarial network for generating faces of celebrities.

  • Tools: Pickle, Matplotlib, PyTorch
  • Implemented a DC-GAN which is trained on the faces of celebrities.
  • The trained model can generate new realistic faces.
TV Script Generation
TV Script Generation

An RNN based model trained on TV Scripts to generate new TV Scripts which can be used by production companies.

  • Tools: Numpy, Pickle, PyTorch
  • Implemented a Recurrent Neural Network which is trained on many existing TV scripts.
  • This algorithm generates new TV Scripts which can be used by a TV show production company.
Income Classification Web App
Income Classification Web App

A web application to predict whether a person earns more than a threshold or not.

  • Tools: Pandas, Seaborn, Scikit-Learn, Streamlit, Heroku
  • Several classifiers from SkLearn library were used to predict whether a person earns more than a threshold or not.
  • Best model was then deployed as a web application using Streamlit on Heroku.
Bike sharing Pattern
Predicting Bike-Sharing Patterns

A deep neural network for bike sharing company.

  • Tools: Numpy, Pandas
  • In this project I Implemented a Deep Neural Network from scratch.
  • The algorithm predicts how many bikes are needed by the company to fulfil the customer requirements on any given day by using the historical data.
Dog Breed Classifier
Dog Breed Classifier

A fine-tuned CNN (VGG-16) to predict the breed of a dog.

  • Tools:Seaborn, Scikit-Learn, PyTorch
  • I implemented a pre-trained Convolutional Neural Network (VGG-16) using transfer learning, fine-tuned it by training on different dog breeds.
  • The algorithm can classify 113 dog breeds efficiently.
Bill Projection
Bill Projection

A linear regression model hourly/monthly bill projection.

  • Tools: Matlab
  • This project takes Date, Time, PV, and Temperature as input data and with the help of machine learning algorithms predicts the monthly residential load demand, which is then further used to calculate the bill of that certain month.
Metabolite Identificatoin

A GUI based software package for Linux for Metabolite Identificatoin.

  • Tools: Shell Scripting
  • This software contains the tools for Metabolite Identification. This software was designed using shell programming and is being currently open sourced.


Languages and Databases

Shell Scripting








Mohamed bin Zayed University of Artificial Intelligence

Abu Dhabi, UAE

Degree: M.Sc. Natural Language Processing
CGPA: 3.68/4.0
Year: 2022 - 2024

    Relevant Courseworks:

    • Advanced Natural Language Processing
    • Deep Learning for Language Processing
    • Topics in Advanced Natural Language Processing
    • Advanced Speech Processing
    • Mathematical Foundations of Artificial Intelligence
    • Foundations of Artificial Intelligence

Nanjing University of Science and Technology

Nanjing, China

Degree: M.Sc. Computer Science and Technology
CGPA: 3.897/4.0
Year: 2021 - 2022

    Relevant Courseworks:

    • Principles and Methods of Artificial Intelligence
    • Machine Learning
    • Data Mining & Big Data Analysis
    • Fundamentals of Image Analysis
    • Pattern Recognition Technology
    • Distributed System and Parallel Computing

University of Engineering and Technology, Lahore

Lahore, Pakistan

Degree: Bachelor of Electrical Engineering
CGPA: 3.747/4.0
Year: 2016 - 2020

    Relevant Courseworks:

    • Data Structures and Algorithms
    • Control Systems
    • Machine Learning
    • Database Engineering
    • Computer Networks
    • Computer Architecture