🤖 Interview Ace Craft — AI/ML Technical Interview Prep

A focused, browser-based practice tool for engineers preparing for AI / Machine Learning technical interviews. Built with React + TypeScript + Vite and powered by Google Gemini AI.

---

✨ Features

---

📂 Question Categories

1. 🖥️ Coding — ML Implementation

Hands-on Python / scikit-learn / PyTorch snippets covering:

• Data cleaning (missing values, scaling, encoding)
• Model training (Logistic Regression, Random Forest, XGBoost, Neural Nets)
• Evaluation metrics (ROC-AUC, F1, confusion matrix)
• NLP pipelines (TF-IDF, tokenization, transformers)
• Feature selection & engineering

2. 🐛 Debug — Data & Model Debugging

Spot and fix common ML bugs:

• Data leakage, shape mismatches, wrong fit/transform order
• Gradient issues, NaN losses, imbalanced datasets
• Pipeline and preprocessing mistakes

3. 🧠 Concepts — ML + LLM Theory

Verbal / whiteboard questions on:

• Bias-variance tradeoff, regularization, overfitting
• Attention mechanisms, Transformers, BERT, GPT architectures
• Embeddings, RAG, fine-tuning, RLHF, prompt engineering
• Evaluation strategies (cross-validation, stratified splits)

4. 🏗️ System Design — Real-World AI Systems

Open-ended design questions:

• Recommendation engines, fraud detection, search ranking
• MLOps pipelines, model serving, A/B testing
• LLM deployment, RAG architecture, vector databases

---

🚀 Getting Started

Prerequisites

• Node.js 18+
• Bun (optional, but recommended — lock file included)

Installation

# Clone the repository
git clone https://github.com/Abhishekmystic-KS/interview-ace-craft.git
cd interview-ace-craft

# Install dependencies
npm install        # or: bun install

# Start the development server
npm run dev        # or: bun dev

Open http://localhost:5173 in your browser.

Build for Production

npm run build
npm run preview

---

🤖 AI Code Chat (Gemini)

The floating 💬 button opens an AI-powered chat panel where you can:

1. Paste a code snippet from any question.
2. Ask questions like "What does this do?", "Where could this break?", or "Optimize this."

Setup:

1. Click the ⚙️ gear icon in the top-right corner.
2. Paste your Google Gemini API key.
3. The key is saved only in your browser's localStorage.

---

🗂️ Project Structure

src/
├── components/
│   ├── CodeExplainChat.tsx   # Gemini-powered AI chat panel
│   ├── MockInterview.tsx     # Timed mock interview session
│   ├── NavLink.tsx           # Navigation link component
│   ├── ProgressHeader.tsx    # Progress bar at the top
│   ├── QuestionCard.tsx      # Expandable question + answer card
│   └── SettingsDialog.tsx    # API key settings modal
├── data/
│   └── questions.ts          # All 100+ AI/ML questions
├── hooks/
│   └── useQuestionStatus.ts  # localStorage progress tracking
└── pages/
    └── Index.tsx             # Main page — search, filter, list

---

🛠️ Tech Stack

---

🧪 Running Tests

npm run test          # run once
npm run test:watch    # watch mode

---

📝 Contributing

1. Fork the repo and create a feature branch.
2. Add or improve questions in src/data/questions.ts following the existing Question interface.
3. Run npm run lint and npm run test before opening a PR.

---

📄 License

MIT — feel free to use, modify, and share.