🤖 AI/ML Engineer | Software Engineer | Computer Vision Specialist

Building intelligent, production-grade systems with Machine Learning, Computer Vision, and full-stack engineering

I'm a passionate AI/ML Engineer and Software Developer with hands-on experience building production-grade machine learning systems, computer vision applications, and intelligent web services. I specialize in translating complex machine learning concepts into scalable, real-world solutions.

Currently completing my AI/ML Internship at DEVFORGE (Jul – Sep 2026), where I develop end-to-end machine learning pipelines, RAG-based conversational systems, and deploy production-ready applications. Previously interned with DevelopersHub Corporation, gaining expertise in model development, feature engineering, and deployment strategies.

I combine theoretical knowledge with practical engineering to deliver solutions that solve real business problems. Passionate about open-source contribution, continuous learning, and mentorship.

Bachelor of Science in Software Engineering
The University of Faisalabad, Pakistan
📚 Focus Areas: AI/ML, Data Structures, Software Architecture, Capstone Project: Smart Queue Management System

July 2026 – September 2026

• Developing production-grade ML systems and intelligent web applications with measurable impact
• Building RAG-based chatbots with LangChain, ChromaDB, and enterprise-grade LLMs
• Implementing zero-shot and few-shot classification pipelines for NLP tasks
• End-to-end ML pipeline design with scikit-learn, Pandas, and advanced preprocessing techniques
• Deployed models achieving 80%+ accuracy with optimized training pipelines

• Developed and deployed machine learning models for real-world predictive analytics
• Conducted comprehensive exploratory data analysis (EDA) and feature engineering on large datasets
• Implemented linear regression and classification models with performance validation
• Optimized data preprocessing pipelines, reducing model training time by 25%
• Collaborated on ML architecture decisions and model evaluation frameworks

Computer Vision | YOLOv8 | OpenCV | Python | Production-Ready

AI-powered intelligent surveillance system with real-time object detection, automated threat detection, and email alert generation. Deployed with SMTP integration for instant notifications.

Key Metrics: 30+ FPS processing | 92% detection accuracy | Multi-class threat classification

🔗 View Repository |

NLP | FastAPI | React | Full-Stack Deployment | Production-Grade

Premium sentiment analysis application classifying text into Positive/Neutral/Negative with confidence scores and comprehensive analytics.

Features:

• Backend: FastAPI microservice with TF-IDF, Logistic Regression, NLTK preprocessing
• Frontend: Glassmorphic React UI with real-time API integration and response visualization
• Deployment: Live on Vercel (Frontend) & Render (API Backend)
• API Docs: Interactive Swagger UI & ReDoc documentation

Key Metrics: 80%+ accuracy | <200ms API response time | 500+ test cases validated

🔗 View Repository |

LangChain | ChromaDB | Streamlit | Groq LLM (Llama 3.1 70B) | Python

Production-grade conversational RAG system answering domain-specific questions with semantic understanding and source attribution.

Features:

• RAG Pipeline: Vector embeddings, semantic retrieval, generation with Llama 3.1 70B LLM
• Memory System: ConversationBufferWindowMemory for multi-turn context retention
• Vector Database: ChromaDB with persistent local storage and efficient similarity search
• Evaluation: 8-question benchmark suite measuring latency & relevance scores
• UI: Dark-mode Streamlit application with document source viewer and conversation history

Key Metrics: Sub-2s response latency | 8.5/10 relevance score | 12+ documents indexed

🔗 View Repository |

Zero-Shot & Few-Shot Classification | HuggingFace Transformers | Python | ML Evaluation

Intelligent support ticket routing system using advanced NLP classification strategies with multi-model comparison.

Features:

• Zero-Shot Model: facebook/bart-large-mnli with NLI hypothesis scoring approach
• Few-Shot Model: google/flan-t5-base with prompt engineering for context-aware classification
• Predictions: Top-3 tag recommendations with confidence scores across 10 ticket categories
• Evaluation: Comprehensive metrics (Accuracy, F1, Precision, Recall, Mean Reciprocal Rank)
• Visualization: 9 analysis charts (confusion matrices, performance comparisons, confidence distributions)

Key Metrics: 87% accuracy (Few-Shot) | 78% accuracy (Zero-Shot) | 0.92 F1-Score

🔗 View Repository

Total Commits (2024-2026):     850+
Lines of Code Written:          50,000+
Projects in Production:         7+
Average Model Accuracy:         86%
Deployment Success Rate:        98%

2024 Q1-Q2: Python Fundamentals → Data Structures
            ↓
2024 Q3-Q4: Machine Learning → Scikit-learn & TensorFlow
            ↓
2025 Q1-Q2: Deep Learning → PyTorch & Computer Vision
            ↓
2025 Q3-Q4: Full-Stack Dev → FastAPI + React + Firebase
            ↓
2026 Q1:    NLP & LLMs → LangChain & Transformers
            ↓
2026 Q2:    RAG Systems → ChromaDB & Production Deploy
            ↓
2026 Q3:    Advanced Specialization → Current Focus

✅ Machine Learning — Supervised & unsupervised learning, model evaluation, hyperparameter optimization
✅ Deep Learning — Computer vision, NLP, transfer learning, fine-tuning, prompt engineering
✅ Retrieval-Augmented Generation (RAG) — Vector databases, semantic search, LLM orchestration
✅ Natural Language Processing — Text classification, sentiment analysis, zero-shot & few-shot learning, LLM integration
✅ Computer Vision — Real-time object detection (YOLOv8), video processing, surveillance systems
✅ Full-Stack Development — FastAPI backends, React frontends, API design, end-to-end deployment
✅ Data Engineering — EDA, preprocessing, feature engineering, pipeline optimization
✅ Software Architecture — Clean code, design patterns, scalable systems, production-grade deployment

• 🚀 Collaboration on ML/AI research projects, RAG systems, and production deployments
• 💰 Opportunities in AI/ML engineering roles, data science, full-stack development, and tech startups
• 📚 Knowledge Sharing — discussing ML architectures, LLM optimization, CV best practices
• 🔗 Open Source — contributing to meaningful projects, creating reusable frameworks
• 🎓 Mentorship — mentoring junior developers in ML/AI, learning from senior engineers
• 🎤 Speaking — tech talks, workshops, and knowledge-sharing at conferences
• 📖 Writing — technical articles, research papers, and case studies

💫 If you find my work interesting:
   • Star my repositories ⭐
   • Follow for updates 👀
   • Share with your network 🔄
   • Give feedback & suggestions 💬
   • Connect & collaborate 🤝

Profile Views:     ⬆️ Growing
Repository Stars:  ⭐⭐⭐⭐⭐ 150+
Active Projects:   🚀 25+
Code Contributions:🔥 850+
Community Support: 💪 Active