E
Enzo detects water leaks in buildings using AI-powered IoT sensors, targeting insurers and their policyholders. The tech stack—TypeScript, React, Python, PyTorch, TensorFlow, GCP, AWS—reflects a full-stack product company with ML at its core. Project velocity centers on time-series model development, inference pipeline scaling, and moving pilots to revenue, while active pain points (detection quality, model speed, infrastructure scaling) reveal the typical early-stage ML startup squeeze: models that work in notebooks don't yet work reliably in production at scale.
Tech Stack 10 technologies
What Enzo Is Building
◆Challenges
- Improving detection quality
- Improving model speed
- Pipe water damage costs
- Pilot project scaling
- Success metric alignment
- Growth channel validation
- Preventing water damage
- Scaling ml infrastructure
- Migrating ml prototypes to production
- Reactive claims management in insurance
▲Active Projects
- Pilot-to-rollout execution
- Growth experiments
- Growth analytics
- Ml platform for data ingestion and inference
- Scalable inference pipelines for time-series models
- Data pipelines for iot sensor data
- Key insurer projects
- Time-series leakage detection model development
- Training and inference performance optimization
- Model deployment automation
Hiring Activity
15 roles · 6 in 30d
Department
Seniority
Notable leadership hires: Head of Sales, Head of Customer Success
Company intelligence
