Khadija Subhani
Backend & AI Engineer | Python, FastAPI, RAG Systems
New to Contra
Khadija is ready for their next project!
Social Engineering in Cyber Security - A RESEARCH PAPER
0
47
Adversarial Attacks on AI-Based Robotic Vision Systems - A REASEARCH PAPER
0
38
Synapse — AI-Powered Team Formation & Mentor-Matching Platform
Built as a final year project — an AI-powered platform for team formation and mentor-matching, designed to help students and teams find the right collaborators using data-driven compatibility scoring. Built the Flutter frontend, the core matching engine (a seven-signal composite scoring system with a Random Forest collaboration predictor and SHAP-based explainability), the proximity module, and Firebase Cloud Messaging integration for real-time notifications. Also managed the deployment pipeline — backend on Render, frontend on Netlify. A fully deployed, functioning platform showcasing applied machine learning, mobile development, and real-time system design in one product.
0
48
AskRAG — RAG-Based Codebase Q&A Tool
Built a retrieval-augmented generation (RAG) tool that lets developers ask natural-language questions about any codebase and get accurate, context-aware answers. Designed and built the full backend using FastAPI, with FAISS for vector storage and all-MiniLM-L6-v2 embeddings for semantic search. Integrated Gemini 2.5 Flash for response generation, PostgreSQL/Supabase for data persistence, and GitHub OAuth for secure repo access. Also built the React/Vite frontend and resolved a critical authentication bug involving JWT cookie handling. A working prototype demonstrating practical LLM application design — from embedding pipelines to secure auth flows.
Project link: https://github.com/khadijayy/askrag
0
75