Matchr - GenAI SaaS for targeted CVs and ATS scoring
The challenge
A useful job-search assistant must do more than rewrite text. It needs structured scoring, anti-invention rules, quotas, billing and a workflow the candidate can trust.
What I built
Matchr starts from a pain every candidate knows: ~70% of CVs are filtered by a robot — the ATS — before a human reads them. The product gets your CV past that filter, with a before/after score, without inventing a skill you don't have. The real subject isn't the UI, it's running an AI product in production: invention is made technically impossible (an invariant strips any skill absent from the source CV), AI cost is bounded (a plan that doesn't clear a 2x margin is refused at deploy), with auth + 2FA, Stripe billing, quotas, a public API, GDPR and PostgreSQL behind it.
It shows how I turn an AI feature into a real product surface with business guardrails — cost, billing, GDPR, anti-hallucination — not a one-off prompt demo.
Key engineering points
Structured CV tailoring flow with role-specific scoring.
Anti-invention constraints so the model cannot add unsupported experience.
Quota, billing and account boundaries for a real SaaS surface.
API-first thinking for future integrations.
Similar technical risk?
I can help scope the risk, architecture and first deliverable.
A 30-minute first call is enough to see whether I am the right profile for the problem.
A similar challenge?
A system like this one to build? Let's talk.
I take on critical technical work — from scoping to production, no debt or lock-in once it's handed over. Fastest way to see if it fits: a 30-minute call.
I reply within 24h — often sooner.