Skip to content

Recruitment · Dome Infosys

Jobscater

Generative AI for a job platform

Job posts generated from a few words, and a CV maker that scores like an ATS and explains what's wrong.

A score alone is useless. The explanation is the product.

How it works

Two sides of the same problem: employers write thin job posts because writing a full one is tedious, and candidates get filtered out by applicant tracking systems without ever being told why.

For employers, a few words about a role expand into skills, keywords, responsibilities and a full specification. For candidates, the CV maker writes a summary, suggests skills, scores the CV the way an ATS would and explains what's dragging the score down — then generates interview questions from what's actually in their CV.

None of it is a chat window, so the output has to be valid structured JSON every time rather than prose that happens to parse. That turned out to be most of the work.

Contact

Let's talk.

Open to AI engineering roles, and happy to talk about retrieval, grounding, or getting a model to work in a language it wasn't really built for.