Hi!
I am Usman Yaqoob
And I Love
Machine Learning / Deep Learning,
Data Science,
Artificial Intelligence :)

Contact

About Me

WHO AM I?

As a Computer Engineering graduate, my passion lies in the realms of Artificial Intelligence, Machine Learning, and Data Science. I derive immense satisfaction from meticulously cleansing datasets, ensuring their optimal utilization. My expertise extends to conducting insightful Data Analysis on real-world datasets and presenting findings through compelling visualizations. I take delight in the process of training Machine Learning and Deep Learning models, instilling programs with the intelligence to make informed decisions. Beyond development, I relish showcasing my work to the world by deploying models on web or app platforms. It's not just about coding; it's about crafting intelligent solutions that resonate with real-world challenges.

Education

Computer Engineer!

I completed my Computer Engineering from University of Engineering and Technology, Peshawar. I completed my engineering degree in the year of 2023 with 3.41 CGPA (out of 4). The major subjects that I studied during my 4 years are:

  • Computer Fundamentals
  • Computer Programming (C++)
  • Calculus
  • Object Oriented Programming (C++)
  • Probability and Statistics
  • Web Engineering (HTML, CSS, Javascript)
  • Data Structures and Algorithms
  • Linear Algebra
  • Operating Systems (C, Linux)
  • Computer Organization and Architecture
  • Systems Programming (C)
  • Signals and Systems (MATLAB)
  • Digital Signals Processing (MATLAB)
  • Database Management System (MySQL, SQL)
  • Data Analytics (Python, Statistics, Machine Learning)
  • Computer Security

Skills

Python

  • Conditional Programming in Python
  • Data Structures in Python
  • OOP in Python

Machine Learning

  • Supervised Learning Algorithms
  • Unsupervised Learning Algorithms
  • Scikit Learn
  • Recommendation Systems

Web Technologies

  • Django
  • Fast API
  • Flask
  • Dash

Data Analysis & Visualization

  • Numpy
  • Pandas
  • Matplotlib
  • Seaborn
  • Plotly
  • Power BI

Deep Learning

  • Neural Networks
  • Natural Language Processing
  • Computer Vision
  • Tensorflow
  • Pytorch
  • Keras

Generative AI

  • Langgraph
  • LangChain
  • LlamaIndex
  • Prompt Engineering
  • RAG
  • Finetuning

Others

  • Data Structures and Algorithms
  • C++
  • C
  • MATLAB
  • SQL
  • Problem Solving

My Favourite Personal Projects

gwspace

A Python library for interacting with Google Workspace APIs like Gmail, Tasks, Sheets, Slides, and more in an easier and efficient way. It was created specifically for building AI agents and automation workflows, making Google Workspace integration smoother for developers and automation systems.

Check here

MailCalDoMeet

An AI agent for Gmail, Google Calendar, Google Tasks, and Google Meet that can send and read emails, create and fetch calendar events, delete tasks and events, manage Google Tasks, and control Google Meet functionalities. It is designed to streamline daily productivity and workflow automation across Google Workspace services.

GitHub Demo

Scratch GPT

This project includes scratch implementations of scalable self-attention, causal self-attention, and multihead attention, along with data preparation scripts for training GPT-2 from scratch. It also covers building the GPT-2 architecture using PyTorch, pretraining it on a textual dataset, classification fine-tuning on a spam/ham email dataset without Hugging Face, and instruction fine-tuning GPT-2 using custom training functions and data loaders from scratch.

GitHub

Experience

Associate Data Scientist TenX 06/2025 - Present

My Contributions

  • Worked on building strategic multi-agent systems to support decision-making and planning for high-impact business use cases.
  • Developed agentic workflows to support medical marketing strategy and other strategic business-related initiatives.
  • Currently working on inventory optimization using machine learning and data-driven forecasting approaches.
Artificial Intelligence Engineer JMM TECHNOLOGY 09/2023 - 06/2025

My Contributions

A. Cryptocurrency Trading Bot Development:

  • Trained models (XGBoost, Random Forest, Decision Tree) for forecasting Ethereum's closing value over the next 4 hours using historical Ethereum data and market fear & greed data. Selected XGBoost due to lowest RMSE.
  • Developed a Random Forest model to predict the best APR by analyzing protocol APRs, coin-specific APRs, and news sentiment from cryptocurrency news data.
  • Created a real-time prediction pipeline that extracts coin APR data, protocol APR data, news sentiment, and market fear & greed data to forecast APRs based on user input.

B. Riyadh's Different Places Reviews Sentiment Analysis and Analytics:

  • Analyzed 2.1M reviews of different places in Riyadh to extract sentiments and aspects, determining whether feedback was positive or negative.
  • Achieved 50% cost savings by using OpenAI GPT-4 batch API for sentiment extraction.
  • Delivered actionable insights by identifying top liked aspects and negative pain points for place owners to improve services.

C. Airport Guidance for Disabled People (MVP):

  • Trained and finetuned Yolov8 and Yolov5 for American Sign Language (ASL) Detection to assist disabled travelers at Saudi airports.
  • Built a system that detects ASL and converts it into text for real-time guidance.
  • Developed a chatbot to answer common queries of disabled passengers.

E. ProofLingo:

  • Developed an AI system that detects contextual errors, missing translations, consistency issues, and incorrect translations in Spanish, French, and Arabic documents compared to the English source, saving up to 5 hours of proofreading.
  • Collaborated on backend development in Django.
  • Deployed the backend on AWS LightSail using Docker for scalability.

F. HRM:

  • Developed an employee facial recognition system for an HRM mobile app to automate login and attendance, deployed on Alibaba Cloud.
  • Built an AI Resume Scoring system to automate initial resume screening, significantly reducing manual review time.

G. College Football Prediction:

  • Built an ETL pipeline for data extraction from APIs, transforming and loading into BigQuery for production, automating a previously manual process.
  • Trained ML models and built a real-time system allowing clients to update BigQuery data and retrain models dynamically.
  • Implemented a CI/CD pipeline with Google Cloud Run, connected to Git for auto-build and redeployment on each push.

H. Hysabat Business Advisor:

  • Designed and implemented an agentic workflow on a database with 300+ interconnected tables to enable natural language sales insights and automated report generation.
  • Deployed on AWS EC2 for secure, scalable business stakeholder access.
Machine Learning Engineer (Internship) LAB-D TECH LTD 07/2023 - 08/2023

My Contributions

  • Developed and optimized a Human Face Recognition System for a school using MTCNN and ResNet to recognize authorized people and send requests to admin when unauthorized access is detected.
  • Optimized the overall recognition system by improving recognition accuracy and reducing FPS lag.