DEV Community: sage106

AI Interview Simulator: Prep Faster, Ace the Interview, and Go Touch Grass published: true

sage106 — Sat, 10 Oct 2026 20:43:36 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass

What I Built

Preparing for interviews is notoriously draining. Developers and professionals spend hundreds of hours glued to screens grinding through static question banks and repetitive mock sessions.
AI Interview Simulator was built to solve this: a high-efficiency pair interviewer powered by open-source AI that delivers hyper-focused practice. Upload your resume or choose your field, run a realistic 5-minute drill, get instant answer coaching and model solutions, and **close your laptop to go touch grass.

Key Highlights:

📄 Resume Personalization: Upload your PDF/TXT resume to get questions that target your actual projects and claimed tech stack.
🌱 Broad Career Disciplines: Not just coding — includes Environmental Sciences, Healthcare Administration, Clinical Research, Field Operations, and Business Management.
💡 "How to Improve Your Answer" Coaching: Pinpoints missing elements (STAR technique, edge cases, metrics, trade-offs).
✨ Ideal / Model Answers: An interactive reveal toggle showing the exact industry-standard response expected by hiring managers.

- 📈 Comprehensive Report: Instant circular scoring, hiring decision recommendations, top strengths, and growth areas.

Demo

🌐 Live Web Application: https://ai-interview-simulator-nu-weld.vercel.app/

- ⚡ Live API Service: https://ai-interview-simulator-9v89.onrender.com/

Code

The entire codebase is open-source:

sage106 / ai-interview-simulator

🤖 AI Interview Simulator

Practice job interviews with an AI powered by open-source LLMs via Groq. Get real questions, instant feedback, and a full performance report — free.

Built for Hacktoberfest 2026 Open-Source AI Challenge.

🌐 Live Demo (Frontend): https://ai-interview-simulator-nu-weld.vercel.app/
⚡ Live API (Backend): https://ai-interview-simulator-9v89.onrender.com/

✨ Features

📄 Resume-Driven Customization — Upload your resume (PDF/TXT) or paste your experience; AI inspects your actual tech stack, past companies, and project achievements to generate tailored, deep-dive interview questions
🎯 Multi-Industry Career Fields — Pre-configured for Tech, AI & Data, Product & Management, Design, Marketing & Sales, Finance & Accounting, and Healthcare & Sciences. Also supports custom write-in roles for any profession.
📊 3 Experience Levels — Junior, Mid, Senior
💬 3 Interview Types — Technical, Behavioral, Mixed
💡 "How to Improve Your Answer" Coaching — Actionable advice on how you can elevate your specific answer (e.g., structuring with STAR…

View on GitHub

- GitHub Repository: https://github.com/sage106/ai-interview-simulator

How I Built It

Frontend: Built with React 18, Vite, Tailwind CSS, and Lucide Icons, deployed on Vercel.
Backend: Node.js & Express with multer and pdf-parse for in-memory resume extraction, deployed on Render.
Database: MongoDB Atlas storing session logs, candidate scores, and coaching breakdowns.

- AI Engine: Open-source large language model (`qwen/qwen3.8-27b`) via high-speed Groq API for zero-latency question generation and structured JSON evaluations.

Why Does Open Innovation Matter?

Open-source AI and open-weight models democratize career preparation:

Privacy & Data Sovereignty: Candidates upload sensitive career histories and resumes. Open-source models allow self-hosting and zero data retention, ensuring personal data isn't locked inside proprietary corporate models.
Accessible Career Coaching for Everyone: Professional mock interviews often cost upwards of $100/hr. Using open-source models with sub-second inference makes high-caliber career coaching accessible to any candidate worldwide for free.

3. Modularity & Flexibility: We can swap, fine-tune, or calibrate evaluation prompts across diverse domain vocabularies without vendor lock-in.

Prize Categories

Best Use of Render: The backend API service is deployed and running live on Render Web Services.

- Best Use of MongoDB Atlas: All session transcripts, resume context, and historical evaluations are stored in MongoDB Atlas.

Built with ❤️ for #hf26challenge!

Building an Open-Source AI Mock Interviewer with Resume Personalization & Answer Coaching published: true

sage106 — Sat, 10 Oct 2026 20:37:06 +0000

🎃 Hacktoberfest 2026: The Open-Source AI Challenge
Preparing for high-stakes interviews is often stressful. Static question lists don't recreate the pressure of dynamic conversations, nor do they probe into a candidate's actual resume claims.

For Week 1 of the Hacktoberfest Open-Source AI Challenge, I built AI Interview Simulator — an intelligent pair interviewer powered entirely by open-source LLMs.

🚀 Live Demo & Links

🌐 Live Demo (Frontend): https://ai-interview-simulator-nu-weld.vercel.app/
⚡ Backend API (Render): https://ai-interview-simulator-9v89.onrender.com/

- 💻 GitHub Repository: https://github.com/sage106/ai-interview-simulator

💡 Key Features

📄 Resume-Driven Question Generation: Upload your resume (PDF/TXT) or paste your experience. The AI analyzes your projects, tech stack, and career timeline to generate customized questions targeting your background.
🎯 Multi-Industry Support: Pre-configured paths across Tech, AI & Data Science, Product, Design, Marketing & Sales, Finance, and Healthcare (plus custom career write-in support).
💡 "How to Improve Your Answer" Coaching: Instead of just a numerical score, candidates receive concrete coaching on how to elevate their response (structure with STAR method, cite trade-offs, metrics, edge cases).
✨ Ideal / Model Answers: An interactive reveal toggle showing the exact industry-standard response a senior hiring manager looks for.
📈 Comprehensive Evaluation: Circular score meter, hiring decision recommendations (Strongly Recommend, Recommend, Needs Work), top strengths, and areas to improve.

6. 💾 MongoDB Session History: Stores previous sessions to track performance over time.

🛠️ Tech Stack

Frontend: React 18, Vite, Tailwind CSS, Lucide Icons (deployed on Vercel)
Backend: Node.js, Express, Multer, pdf-parse (deployed on Render)
Database: MongoDB Atlas

- AI Core: Open-Source LLMs (via high-speed Groq API)

🧠 Architecture Flow


text
Candidate Resume (PDF/TXT) ──> pdf-parse extraction
                                   │
                                   ▼
Open-Source LLM (Groq) ──────> Dynamic Role/Resume Question ──> Candidate Response
                                   │
                                   ▼
Open-Source LLM (Groq) ──────> Dual Evaluation:
                               ├─ Score & Assessment Feedback
                               ├─ "How to Improve" Action Plan
                               └─ Model / Correct Answer
                                   │
                                   ▼
Session Completed ───────────> Comprehensive Report & MongoDB Session Storage

Starting My Hacktoberfest 2026 Journey

sage106 — Thu, 01 Oct 2026 21:01:56 +0000

Hey everyone!

I've been wanting to get into open source for a while, and I finally decided to start with Hacktoberfest 2026.

I'm a B.Tech CSE graduate and mostly work with Java, JavaScript, React, Node.js, Python, SQL, and a few AI/LLM tools. I've built a bunch of projects while learning, but I've mostly been working on my own.

Now I want to see what it's actually like to work on a real open-source project — understanding someone else's code, fixing things, learning from other developers, and hopefully making some useful contributions along the way.

For this Hacktoberfest, I'm mainly looking forward to:

Making my first meaningful open-source contribution

Getting better at Git and GitHub

Working with real-world codebases

Learning more about AI and open-source projects

Meeting other developers who are also starting or contributing to open source

I honestly don't know how this journey is going to go, but that's kind of the fun part.

If you're participating in Hacktoberfest too, feel free to say hi. I'd love to connect and learn from you! :)

Let's see where this goes. 🚀

Hacktoberfest2026 #Hacktoberfest #OpenSource #GitHub