Gridware is looking to build fleet health predictive models, thresholds, and optimization frameworks to ensure 99% uptime across their rapidly scaling network of IoT devices, which are crucial for monitoring and enhancing the electrical grid's reliability and safety.
Requirements
- Expertise in forecasting, anomaly detection, and predictive modeling, with experience handling time-series, sensor, or geospatial datasets.
- Proficiency in Python with scientific and ML libraries (NumPy, Pandas, SciPy, scikit-learn, Keras, PyTorch) and familiarity with data platforms (SQL, Spark, etc.).
- Experience forecasting solar generation, connectivity performance, or energy resource availability.
- Exposure to distributed sensing systems in energy, seismic monitoring, aerospace, industrial IoT, or environmental science.
- Background in working with power-constrained, communication-constrained, or solar-powered devices.
- Experience scaling predictive systems across large and growing hardware fleets.
Responsibilities
- Develop predictive and forecasting models to anticipate device health issues, solar availability, and connectivity performance, driving proactive interventions and deployment planning.
- Define, test, and refine health thresholds to classify degradations, detect regressions, and optimize fleet performance across diverse operating conditions.
- Design and evaluate statistical tests and simulations to measure impact, uncover downtime drivers, and identify optimization opportunities.
- Collaborate with engineering, fleet operations, and software teams to embed intelligence into automated monitoring and remediation pipelines at scale.
- Communicate insights and contribute to scalable fleet intelligence frameworks that support growth from tens of thousands to millions of devices.
Other
- 3+ years of applied experience in data science with large-scale, real-world systems (IoT, clean tech, connectivity, or related domains).
- Strong communicator with the ability to design experiments, validate models, and translate technical findings into actionable insights for cross-functional teams.
- Bachelor’s or Master’s degree in Engineering, Statistics, Data Science, or a related quantitative field.
