Moveris
Anti-fraud · AI liveness
Digital identityNow
Senior Backend Engineer · Anti-fraud and AI
Context
The product answers two questions: whether there is a real person on the other side of the screen, and whether the content they send was machine-generated. Both are now a requirement in any digital onboarding.
The challenge
Answering in real time over an API, without turning verification into a signup bottleneck, and keeping the system current against impersonation techniques that change every few months.
What it does
- Real-time fraud detection over API
- Liveness: real-person verification
- Identification of AI-generated content and video
What I did
- Real-time fraud detection and human-liveness APIs.
- Identification systems for AI-generated content and video.
- Wrapped the models behind stable API contracts, so the product does not depend on the specific shape of each model.
Stack
- Python
- FastAPIInference APIs
- AI
- MCPComputer visionLivenessAI content detection
- Data
- RedisObject storage
- Infrastructure
- DockerAWS
Services practised here
- Cloud, DevOps & IaCInfrastructure ends up described as code and deployment automated, so shipping to production is routine and anyone on the team can do it.
- AI Integration & AutomationModels and agents go into the product you already have with the same discipline as any other service: a contract of your own, cost limits and a log of what they did.