Data Scientist / ML Engineer — Water Infrastructure

Strong data science fundamentals (modeling, validation, interpretation) and solid data engineering skills (pipelines, APIs, data quality) Python — must have Comfortable with ambiguous, messy real-world data Nice to have: Go, TypeScript Bonus: experience in water/utilities, environmental, or industrial IoT domains Bonus: time-series, anomaly detection We build ML systems that help water utilities and infrastructure operators predict and prevent failures — sewer overflows, flood risk, infrastructure breakdowns. Real-world impact, real sensor data, real consequences when the model gets it wrong. Small, distributed team across Poland and Canada. ,[Own the full pipeline-to-model workflow: from raw, messy sensor/telemetry data to production-ready predictive models, Build and maintain the data pipelines your own models depend on, Work directly with utility operators and engineers — your models inform real operational decisions, Shape our approach to anomaly detection, time-series forecasting, and physics-informed ML, Collaborate across a distributed team (Poland + Canada)] Requirements: Python, SQL, Machine learning, Kubernetes Tools: Confluence, GitHub, GIT, Agile, Scrum. Additionally: Training budget, Small teams, Flat structure, International projects, Free coffee, Bike parking, Shower, Free parking, No dress code.