I am Nihal Ali, a Bachelor of Science in Artificial Intelligence student at FAST-NUCES with a passion for Machine Learning, Deep Learning, and Data Analytics. I specialize in developing AI-driven applications, predictive modeling, and end-to-end data pipelines.

I actively participate in Kaggle competitions, open-source contributions, and hackathons to refine my skills. Beyond coding, I lead initiatives and mentor others, believing in the power of collaboration and knowledge sharing.

• Python (pandas, NumPy, scikit-learn, TensorFlow, PyTorch)
• SQL (PL/SQL)
• Java, R, C++, C

• SQL Server, MySQL, PostgreSQL, Oracle, MongoDB

• Azure Basics, Git/GitHub, Docker, MLOps

• Scikit-learn, TensorFlow/Keras, OpenAI, Hugging Face, NLTK

Technologies: React Native, Python, OpenAI, CI/CD, Render

• Engineered a production-ready GenAI mobile app facilitating roleplay-based communication training with emotionally intelligent personas.
• Architected a robust DevOps pipeline (GitHub Actions, EAS, Render) to automate backend deployments and Over-the-Air (OTA) updates.

Technologies: Python, Streamlit, Sentence-Transformers, NLTK, Scikit-learn

• Developed an intelligent bidirectional matching engine that ranks CVs against Job Descriptions using a Hybrid AI approach (Vector Space Model + Bi-gram Language Modeling).
• Optimized retrieval accuracy by implementing semantic embeddings (all-MiniLM-L6-v2) and statistical pattern matching with a weighted scoring algorithm.
• Built a real-time recruitment dashboard in Streamlit, featuring automated PDF parsing, percentage-based compatibility scoring, and interactive ranking for both recruiters and candidates.

Technologies: Python, OntoGen, scikit-learn, NLP

• Developed an ontology-driven essay grading system using OntoGen and Linear Regression.
• Processed text using NLTK & spaCy for structured evaluation.

Technologies: Python, scikit-learn, Tkinter

• Achieved 95% accuracy using Random Forest Classifier for T20I match predictions.
• Built an interactive GUI for real-time predictions and data analysis.

Technologies: Python, LSTM, VGG16, Tkinter

• Developed an LSTM-based caption generator with VGG16 feature extraction.
• Achieved 87.3% accuracy and a BLEU score of 0.47.

Technologies: Python, LSTM, Keras, scikit-learn, Plotly

• Built an LSTM model for Tesla stock price prediction (2010-2023).
• Visualized trends with candlestick charts using Plotly.

• Gold Medalist – Secured 5A*s, 4A’s in GCSE O Levels
• Highest Achiever Award – Grade 9, 10
• Merit Citation Award – Sidhpur Development Foundation (Grade 9, 10)
• Best Patrol Leader Award – Al Azhar Garden Boy Scouts Unit

• Career Lead at AAGSA (Al Azhar Garden Students' Association)
• Organized Career Fest 2024 as Event Lead
• Head Teacher at Al Azhar Garden Religious Education
• Rover Scout at AAG Boy Scouts Unit

🚀 Let's build something amazing together!