Matching.
Recommendation systems for human compatibility.
Recommendation systems for human compatibility. Productionized.
Multi-signal matching engines that combine collaborative filtering, embedding similarity, and explicit preference logic. We train, evaluate, and ship the entire pipeline, from feature extraction to the reranker that decides what shows up at the top of the feed.
Common deployments
What we ship
- Production ranking service with A/B harness wired in.
- Reviewer dashboards for ML drift and quality monitoring.
- Feature store with documented schema and SLAs.
- Runbook for retraining cadence and rollback.
Five components, one cohesive runtime.
We build each layer to operate independently, then compose them into the brands we run for our members.
Feature pipeline
Streaming + batch features, served from a low-latency store.
Embedding service
Vector encoders for profile, behavior, and content signals.
Two-tower retrieval
Approximate nearest neighbor search at sub-50ms p99.
Reranker
Gradient-boosted reranker tuned to business-defined success metrics.
Feedback loop
Implicit and explicit signal ingestion with A/B harness.
We pick boring, proven tools where boring works. Where the problem demands more, we build deliberately on top of these primitives.
What it looks like in production.
Day-7 retention lift (typical)
End-to-end recommendation latency
Recommendation acceptance rate
Often paired with these primitives.
All six pillarsReal-time messaging at conversational latency.
WebRTC infrastructure for face-to-face connection.
Moderation as a recommendation problem.
Proof-of-personhood without surveillance.
Subscriptions, micro-payments, regional rails.
Building the systems that bring people together.
Questions about our brands, press, or partnerships? Send a note and we'll reply within two business days.