AI Water Quality Prediction Engineer

Zelux Studio

Remote · $130k – $160k / year · Full-time · Posted 4 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Waterborne disease outbreaks are almost always detectable before they become health crises — if you're monitoring the right signals. Turbidity spikes, chlorine residual drops, pathogen DNA traces in wastewater, temperature anomalies in distribution networks: these signals precede incidents by hours to days. We build the ML systems that help municipal water utilities and environmental regulators detect those signals before people get sick. Our platform monitors 340 water systems across North America and the EU, processing sensor telemetry, lab test results, and satellite-derived watershed data in near-real-time. The prediction challenge is multi-target: contaminant type matters as much as contamination presence, and the tolerance for false negatives (missed real threats) is much lower than for false positives. You'll own the prediction model stack: redesigning from single-sensor threshold models to multi-modal fusion that combines sensor arrays, historical patterns, and upstream watershed events. You'll also build the calibration framework that lets each utility configure the sensitivity trade-off appropriate for their risk tolerance and regulatory context.

Fully remote.

Responsibilities

Redesign water quality prediction models from threshold-based to multi-modal ML
Build fusion models combining sensor arrays, lab results, and watershed remote sensing
Develop per-utility sensitivity calibration reflecting regulatory risk tolerances
Implement real-time prediction serving with sub-60-second latency from sensor event
Create evaluation frameworks calibrated to public health impact, not just accuracy metrics
Collaborate with water safety domain experts and municipal utility partners

Requirements

6+ years in environmental data science, IoT ML, or public health analytics
Experience with multi-sensor fusion and time series prediction under sparse labels
Strong Python, PyTorch, and distributed computing skills
Understanding of water quality monitoring frameworks and regulatory standards
Ability to collaborate with non-technical domain experts and government clients