Hi, I’m Engr. Eesha Khan, a PEC Level 2 Software Engineer specializing in Machine Learning, AI, and Data Science. I build intelligent systems and data-driven solutions that address complex, real-world challenges, including predictive models, AI-powered applications, and scalable data pipelines.I actively engage in hands-on projects and competitive platforms, exploring new technologies to enhance the effectiveness and reliability of AI systems. My goal is to contribute to innovative solutions that combine technical rigor with practical impact, while continuously growing in the evolving AI landscape.

Deep Learning & NLP: BERT, DeBERTa, CNNs, RNNs LLMs & GenAI: LangChain, Ollama, Groq API

Problem: Manual telecom regulatory compliance auditing requires auditors to review large volumes of policies, advisories, regulatory documents, and asset records to determine compliance with CTDISR controls.

Approach: Developed an AI-powered compliance auditing platform using Retrieval-Augmented Generation (RAG). The system processes PDF, DOCX, and Excel documents through parsing, chunking, embedding, and FAISS-based vector search. A fine-tuned Llama model uses retrieved regulatory evidence to generate PTA responses, recommendations, and action items for selected CTDISR controls.

Technology: Python, FastAPI, React, FAISS, Sentence Transformers, Llama 3.2, LoRA/QLoRA, Docker.

Outcome: Developed an end-to-end compliance audit workflow that enables administrators to manage regulatory knowledge sources and auditors to run AI-assisted CTDISR control audits, review generated findings, add NTC comments, and manage audit reports.

Link: https://github.com/EngrEeshaKhan/AI-Powered_PTA-CTDISR-Compliance-Audit-System

Problem: Users cannot reliably query and extract information from large PDF documents using standard chatbots. Approach: Applied Retrieval-Augmented Generation to retrieve and generate relevant document context. Outcome: Enabled accurate, context-aware question answering over uploaded documents. Link: https://github.com/EngrEeshaKhan/rag-chatbot.

Problem: Writing professional outreach emails is time-consuming for job seekers and freelancers. Approach: Used a large language model to generate structured cold emails from user input. Outcome: Reduced email drafting time while improving message clarity and professionalism. Link: https://github.com/EngrEeshaKhan/AI-Powered-Cold-Email-Generator-Job-Client-Outreach.

Problem: Early indicators of problematic internet use in children are difficult to detect manually. Approach: Built a predictive model using behavioral and physical activity data. Outcome: Supported early identification and intervention for healthier digital habits. Link: https://github.com/EngrEeshaKhan/Child-Mind-Institute-Problematic-Internet-Use

Problem: Manual identification of protein complexes in cryo-electron tomography data is slow and inefficient. Approach: Applied deep learning models to classify protein structures from 3D tomographic data. Outcome: Enabled scalable and automated biological structure analysis. Link: https://github.com/EngrEeshaKhan/CZII-CryoET-Object-Identification.

Problem: Early melanoma detection from skin images is challenging due to subtle visual differences. Approach: Applied DIP and handcrafted feature extraction followed by ML classification. Outcome: Improved accuracy and reliability of melanoma detection. Link: https://github.com/EngrEeshaKhan/Automatic-Melanoma-Detection-using-Hybrid-Features-and-Machine-Learning-Models.

Problem: Manual essay grading is time-consuming and inconsistent. Approach: Used NLP-based models to evaluate essays based on structure, coherence, and semantic quality. Outcome: Produced automated scores closely aligned with human evaluation. Link: https://github.com/EngrEeshaKhan/Learning-Agency-Lab---Automated-Essay-Scoring-2.0

Role: AI Engineer
Organization: National Telecommunication Corporation (NTC)

Duration: April 2026 – September 2026

Responsibilities / Achievements:
-Developed AI and RAG solutions for policies, advisories, tenders, and regulatory documents.
-Built document pipelines for PDF, DOCX, and Excel processing, chunking, embeddings, and retrieval.
-Developed policy, advisory, and tender comparison/analysis workflows using AI.
-Built and fine-tuned Llama 3.2 using LoRA/QLoRA for domain-specific tasks.
-Developed the AI-powered PTA CTDISR Compliance Audit System for automated audit analysis and recommendations.
-Built FastAPI APIs and a React frontend for AI applications and workflows.
-Implemented vector search, RAG retrieval, AI inference, and prompt engineering.
-Containerized applications using Docker and Docker Compose.

Role: ML Intern
Organization: Ezitech Institute Rawalpindi

Duration: June 2025 – August 2025

Responsibilities / Achievements:

• Designed and implemented end-to-end ML pipelines for data preprocessing, feature engineering, model training, and evaluation.
• Developed an essay scoring system using Python, TensorFlow, Scikit-learn, Groq, and Streamlit, improving automated evaluation accuracy.
• Built, fine-tuned, and validated machine learning models for real-world applications.
• Prepared detailed reports and presented results to the supervising team, ensuring reproducibility and robustness of models.

Role: Web Developer Intern
Organization: EzeeSol Technology Rawalpindi

Duration: [June 2024 – August 2024]

Responsibilities / Achievements:

• Assisted in front-end and back-end development for web applications.
• Gained experience in [e.g., HTML, CSS, JavaScript, PHP].

Research Area: Computer Vision, Machine Learning
Methods: Support Vector Machines (SVM), Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN)
Status: Published

Research Area: Artificial Intelligence, Healthcare Analytics
Methods: CatBoost, XGBoost, LightGBM, Ensemble Learning
Status: Final Academic Research Manuscript (Unpublished); IEEE Format

Research Area: Digital Twin Technology, Biomedical Signal Processing
Methods: Sparse Identification of Nonlinear Dynamics (SINDy), Physics-Informed Neural Networks (PINN)
Status: Draft Academic Research

Research Area: Natural Language Processing, Educational AI
Methods: Linear Regression, XGBoost, LightGBM, LSTM, BERT
Status: Academic Research Paper

Research Area: Computer Vision, Medical Imaging
Methods: YOLO-based Deep Learning, 3D Tomographic Analysis
Status: Academic Research Paper

1. Hybrid Blockchain–AI Framework for Real-Time Semantic Data Integrity and Access Control in 6G-Enabled IoT Networks.

2. AI-Based Electricity Billing Forecasting and Consumer Classification Using Behavioral Markers.

3. Artificial Intelligence-Based Patient Triage System (PTS) in Healthcare Using Natural Language Processing.

• CZII – CryoET Object Identification: Ranked 536 / 931
• ISIC 2024 – Skin Cancer Detection with 3D-TBP: Ranked 2597 / 2739
• BirdCLEF 2024: Ranked 333 / 974
• Learning Agency Lab – Automated Essay Scoring 2.0: Ranked 2137 / 2706

• AI Engineer Training-ship-National Telecommunication Corporation
• Machine Learning Intern – Ezitech Institute
• Web Development Intern – EzeeSol Technologies
• Machine Learning & Data Science Intern (Demo Training Program) – Edureka

• Kaggle Profile: Active participation in ML, NLP, medical imaging, and audio classification challenges

• Email: engr.eeshakhan@gmail.com
• GitHub: github.com/EngrEeshaKhan
• Kaggle: kaggle.com/eeshakhanzadi
• LinkedIn: linkedin.com/in/engr-eesha-khan-943ba93a5