Shabnam Ansari
Software Development Engineer with 2 internships delivering full-stack and AI-powered applications using React.js, Node.js, MongoDB, Python, and Machine Learning. Built an ML model achieving 85% prediction accuracy on a 1,025-record healthcare dataset and developed 2 production-ready MERN Stack platforms.
Solved 500+ algorithmic problems across LeetCode, CodeChef, HackerRank, InterviewBit, and SPOJ. Strong command of Data Structures and Algorithms, Object-Oriented Programming (OOP), and Software Development Life Cycle (SDLC).
Experience
Engineering Intern
Central Electronics Limited
Delhi, India
Developed an AI-powered sustainable product design solution integrating CAD workflows with ML models, cutting manual material evaluation effort by 40%.
Integrated predictive analytics pipelines across 5 product categories covering lifecycle assessment and environmental impact scoring, improving decision accuracy by 22%.
Reduced assessment turnaround time by 35% by automating data preprocessing and model inference workflows in Python and Scikit-Learn.
Full Stack Developer Intern
Alpha AI
Delhi, India
Engineered 3 full-stack web applications using React.js, Node.js, Express.js, and MongoDB, cutting average page load time by 30% through component-level optimization.
Constructed scalable REST APIs handling 500+ concurrent requests, enabling reliable data exchange between frontend interfaces and backend services.
Accelerated feature delivery by 25% by streamlining debugging and deployment workflows across Agile sprint cycles.
Optimized database queries and backend logic, reducing average API response time by 20% and increasing application throughput by 15%.
Education
Indira Gandhi Delhi Technical University for Women (IGDTUW)
Bachelor of Technology (B.Tech)
Delhi, India
Skills
Projects
Smart Recipe Recommender
React.js, Node.js, Express.js, MongoDB, NLP, Machine Learning
Built a full-stack recommendation platform matching 1,000+ ingredient combinations to recipes using NLP classification models, achieving 88% recommendation accuracy.
Implemented ingredient tokenization and text-analysis pipelines processing 500+ entries, boosting inference speed by 30% compared to baseline preprocessing.
Designed protected route architecture, pagination, and lazy loading, reducing initial bundle size by 40% and supporting 200+ concurrent users.
Deployed ML-backed REST endpoints enabling real-time recipe prediction with sub-200ms average response time.
Heart Disease Prediction Model
Python, Machine Learning, Flask, Scikit-Learn, Pandas, NumPy
Achieved 85% prediction accuracy by training Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine (SVM) models on a 1,025-record clinical dataset.
Automated data cleaning, feature engineering, and exploratory data analysis using Pandas and NumPy, reducing preprocessing time by 60%.
Delivered a Flask web interface exposing REST endpoints for real-time health risk scoring across 3 clinical use cases.
Resolved model interpretability gaps through feature importance ranking and correlation analysis, lowering misclassification rate by 18%.
Achievements
Solved 500+ Data Structures and Algorithms (DSA) problems
LeetCode, CodeChef, HackerRank, InterviewBit, and SPOJ
Established technical workshop programs
Core Team Member of Google Developer Student Clubs (GDSC) IGDTUW
mentoring 30+ junior developers in full-stack and ML skills.
Broadened outreach as a Mentor
Desh Ke Mentor Program, Government of Delhi
guiding 50+ school students through career planning.
Scaled coding education reach
Women in Tech volunteer initiatives
to 100+ student participants.