<h2>The Role</h2>We are looking for an Applied AI/ML Engineer to own the full analytical stack from raw sensor data to actionable grid intelligence. This is not a benchmark dataset problem. The data comes from physical systems operating in complex, variable environments. You will be the technical owner of how GridIQ turns edge data into operational insights.<h2>Responsibilities</h2><ul><li>Signal pipeline architecture — design and maintain the preprocessing pipeline from raw data through filtering, feature extraction, and windowing into ML-ready representations</li><li>Fault detection and classification models — develop, train, and evaluate models for fault type discrimination</li><li>Localization and ranging — own algorithms for event localization; improve accuracy under real-world conditions including noise and environmental variability</li><li>Model deployment — package models for constrained edge hardware and/or cloud inference; define latency and resource budgets</li><li>Model operations — define monitoring strategy, drift detection, and retraining triggers for production deployments</li><li>Evaluation framework — define ground truth labeling strategy, build test harnesses against field-collected and synthetic datasets, own model performance metrics</li></ul><h2>Qualifications</h2><ul><li>Production experience training and evaluating classification or anomaly detection models on time-series or spectral data</li><li>Solid grounding in model evaluation: precision/recall tradeoffs, confusion matrices, calibration, handling class imbalance</li><li>Experience with data pipeline tooling</li><li>Experience with feature engineering from raw sensor data</li><li>Signal processing experience on real sensor data</li><li>Python proficiency: NumPy, SciPy, PyTorch or TensorFlow, scikit-learn or similar</li></ul><h2>Nice to Have</h2><ul><li>Power systems, utility telemetry, or SCADA data experience</li><li>Published work or open-source contributions in applied ML or signal intelligence</li><li>Experience with transmission line theory or RF propagation physics (eg. radar or ultrasound)&nbsp;</li></ul>

GridIQ is building the next generation of grid intelligence for critical infrastructure, starting with wildfire prevention and distribution-level visibility. Today’s electrical grid operates with limited real-time awareness at the edge, where faults occur, outages begin, and wildfires ignite, forcing operators to react after failure using incomplete data. GridIQ addresses this gap with advanced sensing and analytics technology that enables continuous monitoring of distribution networks and delivers high-resolution, real-time insights to support faster, more informed decision-making. Designed for high-risk environments such as wildfire-prone regions, critical infrastructure, and microgrids, our platform integrates with existing systems to improve reliability, reduce risk, and modernize grid operations. We are building a more resilient, intelligent, and proactive energy infrastructure to help protect communities and support the future of electrification.

Applied AI/ML Engineer

<h2>The Role</h2>We are looking for an Applied AI/ML Engineer to own the full analytical stack from raw sensor data to actionable grid intelligence. This is not a benchmark dataset problem. The data comes from physical systems operating in complex, variable environments. You will be the technical owner of how GridIQ turns edge data into operational insights.<h2>Responsibilities</h2><ul><li>Signal pipeline architecture — design and maintain the preprocessing pipeline from raw data through filtering, feature extraction, and windowing into ML-ready representations</li><li>Fault detection and classification models — develop, train, and evaluate models for fault type discrimination</li><li>Localization and ranging — own algorithms for event localization; improve accuracy under real-world conditions including noise and environmental variability</li><li>Model deployment — package models for constrained edge hardware and/or cloud inference; define latency and resource budgets</li><li>Model operations — define monitoring strategy, drift detection, and retraining triggers for production deployments</li><li>Evaluation framework — define ground truth labeling strategy, build test harnesses against field-collected and synthetic datasets, own model performance metrics</li></ul><h2>Qualifications</h2><ul><li>Production experience training and evaluating classification or anomaly detection models on time-series or spectral data</li><li>Solid grounding in model evaluation: precision/recall tradeoffs, confusion matrices, calibration, handling class imbalance</li><li>Experience with data pipeline tooling</li><li>Experience with feature engineering from raw sensor data</li><li>Signal processing experience on real sensor data</li><li>Python proficiency: NumPy, SciPy, PyTorch or TensorFlow, scikit-learn or similar</li></ul><h2>Nice to Have</h2><ul><li>Power systems, utility telemetry, or SCADA data experience</li><li>Published work or open-source contributions in applied ML or signal intelligence</li><li>Experience with transmission line theory or RF propagation physics (eg. radar or ultrasound) </li></ul>

Applied AI/ML EngineerNew

About the Job

About the Company

GridIQ

Similar Jobs

Software Engineer, ML Platform

Software Engineer, ML Platform

Staff Applied ML Engineer

Staff Applied ML Engineer

Senior Backend Engineer - AI Product

Senior Backend Engineer - AI Product