Role Summary
Orca is looking for a hands-on Machine Learning Engineer to develop the intelligence behind our connected water monitoring platform.
The role focuses on applying machine learning to time-series and connected-device data to improve detection, analytics, and decision support across Orca's platform.
This is a practical, applied engineering role. The right person can work from raw data through model development, validation, production integration, and ongoing improvement. You will collaborate closely with software, hardware, product, and operations teams to turn model outputs into useful product capabilities.
Key Responsibilities
· Collect, clean, organize, and prepare sensor and operational data for machine learning development.
· Analyze time-series data to identify meaningful patterns, trends, and anomalies.
· Develop and improve classification, anomaly-detection, and predictive models for Orca's connected water platform.
· Tune models and detection logic for different deployment environments and evolving data patterns.
· Design validation approaches and track model performance using appropriate technical and operational measures.
· Support the development of higher-level analytics, indicators, and decision-support features.
· Work with the full stack team to integrate validated models into production data pipelines, dashboards, alerts, and reporting.
· Document datasets, experiments, assumptions, limitations, and model versions so work is reproducible and maintainable.
Orca Water Solutions
Qualifications
· Degree in computer science, software engineering, computer engineering, data science, statistics, applied mathematics, or a related technical field, or equivalent practical experience.
· Proven experience developing, validating, and deploying machine learning or statistical models using production data.
· Strong Python skills and practical experience with common machine learning and data-analysis frameworks.
· Strong understanding of time-series analysis, anomaly detection, classification, and feature engineering.
· Experience preparing and working with noisy, incomplete, or complex real-world datasets.
· Experience evaluating, monitoring, and improving model performance over time.
· Ability to write clean, maintainable production code rather than limiting work to notebooks or one-off prototypes.
· Experience with SQL, APIs, version control, testing, and cloud-based data workflows.
· Practical technical judgment, clear communication, and a collaborative working style suited to a cross-functional product team.
Advantageous Attributes
· Experience with IoT platforms, telemetry, streaming sensor data, edge devices, or other physical systems.
· Experience with Google Cloud Platform or comparable cloud data and machine learning services.
· Experience with time-series databases, event pipelines, experiment tracking, model registries, or other MLOps practices.
· Experience applying machine learning to industrial, building, utility, or other real-world operational data.
· Experience supporting customer-facing analytics, dashboards, or operational decision tools.
· Experience working with startups or fast-moving product teams where models must produce practical, trustworthy results.
Pay: $70,000.00-$100,000.00 per year
Work Location: In person
