Job Description
Your mission
You'll join
Didit Labs
, our in-house AI lab, and develop
state-of-the-art biometric models — including fraud
— shipped to production and used by millions.
What we're looking for
Deep computer-vision expertise focused on faces
— liveness, anti-spoofing / PAD, recognition, or related. You've built and shipped face models, not just used them.
Strong deep-learning fundamentals
— PyTorch, training pipelines, and the judgment to take a model from SOTA paper to production.
You ship.
You can move from research to a real, fast, reliable service.
High ownership and intensity
— we're a small, lean team that expects a lot and moves fast.
Nice to have
A track record that proves the level — strong publications, a competitive ML record (e.g. Kaggle), or production face-biometrics systems at scale.
What we offer
In-office in Barcelona or San Francisco
— work shoulder-to-shoulder with a tiny, elite team inside Didit Labs.
Real ownership
— you own face biometrics outright, in a Y-Combinator-backed company used by 2,000+ companies.
Real growth




— the chance to build the best identity company in the world, with the resources of a freshly funded lab behind you.
We'll discuss compensation directly during the process.
About us
Didit is
infrastructure for identity and fraud
. We give companies one API to authenticate, verify, and monitor users and businesses — including KYC, KYB, biometric liveness, AML screening, transaction monitoring, and wallet screening — all composable into any workflow and live in minutes.
We're the only identity provider formally attested by an EU member-state government as safer than in-person verification. We offer transparent pricing, 500 free checks per month, and general coverage across 220+ countries, 14,000+ document types, and 48+ languages.
Backed by Y Combinator, we're a small, fast-moving team building the identity and fraud layer for the internet. If you want to ship products used by millions and own meaningful scope from day one, we'd love to hear from you.

📌 Ai Engineer Biometrics (Laza)
🏢 DIDIT
📍 Laza