Rizz AI Gender Service
FastAPI + InsightFace ONNX inference for gender-age signals—isolated from matchmaking with commercial-safe model governance.
2024
FastAPI
Python- InsightFace
- ONNX
NestJS
Context
Face inference is license-sensitive and CPU-heavy—it cannot share a process with sub-second matchmaking without tail-latency risk and unclear model governance.
Build
We isolated ai-service as Python 3.12 + FastAPI with explicit model directories and disabled auto-downloads, exposing narrow REST contracts the NestJS gender-verification module can timeout and degrade gracefully.
Client: Rizz Roulette
Impact
- Gender verification callable without blocking unrelated API traffic
- Clear separation between research-grade weights and production policy
- Room to add future inference modules without monolith growth
More case studies
Go.cam
Age verification · self-hosted
Official AVS flow
Go.cam Age Verification
Official Go.cam open-source age gate—self-hosted alongside Rizz, with encryption keys and callback wiring documented in-repo.
NestJS ↔ Go.cam
POST /age-verification/callbackPolicy gate → match
Rizz Age Verification Integration
NestJS age-verification module—Go.cam SDK callbacks, session state, and policy hooks before users enter match.