Mercor CV Optimizer

Mercor CV Optimizer takes an existing resume and reorganises it around a candidate’s domain, skills and outcomes. Add a target job listing to focus the rewrite on the experience that matters for that role.

The model returns structured data, which a dedicated PDF renderer turns into a consistent, single-column document. The aim is to make real experience easier to find and read, with explicit skills and less filler.

PDF / DOCX → text extraction
           → Claude or OpenAI + optional job listing
           → structured CV → PDFKit → downloadable PDF

PDF text is extracted with pdf-parse; Word documents are read with Mammoth. A structured prompt asks for a clear headline, outcome-led experience bullets and prioritised skills. PDFKit handles the final layout, independently of the model.

The prompt instructs the model to preserve facts and mark missing metrics with placeholders such as [add metric]. Review the output and replace or remove placeholders before submitting it. AI can still make mistakes; this tool does not guarantee a match or offer and is not affiliated with Mercor.

• Start with the CV you have

  Upload a PDF with selectable text or a Word .docx file, up to 8 MB. Scanned, image-only PDFs need text recognition first.

• Tailor to a target role

  Supply a domain and job description to prioritise relevant evidence. The model is instructed to flag requirements that the source CV does not support.

• Two understated PDF layouts

  Choose Executive for navy headings, or Minimal for a restrained monochrome document. Both use selectable text and a single column.

• Your choice of AI provider

  Use Claude or OpenAI with a server-configured key or a key supplied for one request. The CV text and optional listing are sent to the selected provider for processing.