Skip to content

AI CV Builder & Interview Prep

ATS resume generation + voice mock interview

ATS-friendly resume generation, parsing and job-description optimisation, plus a voice-based AI mock interview that gives candidates instant feedback.

AI / LLM

AI CV Builder

ATS-friendly resumes and voice mock interviews with instant AI feedback.

  • Next.js
  • TypeScript
  • PostgreSQL
  • Prisma
  • Groq LLM
  • Whisper

The problem

Job seekers often send CVs that applicant tracking systems (ATS) parse badly, and they rarely get to practise interviews with useful feedback. This platform tackles both: it helps candidates build ATS-friendly CVs tailored to a job description, then lets them rehearse with a voice-based mock interview.

My role

Full-stack development of the platform.

Stack

  • Next.js
  • TypeScript
  • PostgreSQL
  • Prisma
  • Groq LLM
  • Whisper

Architecture

A Next.js and TypeScript app handles the UI and server logic. Resume generation, parsing and job-description optimisation call a Groq-hosted LLM. In the mock interview, Whisper turns the candidate's spoken answers into text, the LLM generates feedback, and text-to-speech reads questions and feedback aloud. Data is stored in PostgreSQL through Prisma.

AI CV Builder system architectureCandidates connects to Next.js app. Next.js app connects to Groq LLM. Next.js app connects to Whisper. Next.js app connects to PostgreSQL.USERSCandidatesWeb + microphoneAPPNext.js appTypeScript · API routesAI + DATAGroq LLMResume + feedbackWhisperSpeech-to-textPostgreSQLPrisma
AI CV Builder system architecture

Key technical decisions

  • Groq LLM for fast responses, so resume suggestions and interview feedback feel immediate.
  • Whisper speech-to-text so candidates answer out loud, as they would in a real interview.
  • Job-description optimisation that compares a CV against a target role before generating changes.
  • PostgreSQL and Prisma for typed access to users, resumes and interview sessions.

Result

Candidates can generate an ATS-friendly CV, optimise it for a specific job description, and get instant feedback from a voice-based mock interview.

Links

This project has no public link. I am happy to walk through it in an interview.