[Hiring] Senior Data Scientist @Technosylva

Role Description

We are seeking a Senior Data Scientist with deep expertise in modeling the impact of extreme weather on electric grid infrastructure, with a particular focus on transmission outage prediction. In this role, you will design, build, and operationalize machine learning and statistical models that predict weather-driven outages and failures across transmission and distribution systems, directly supporting utility decision-making before and during extreme weather events.

You will work at the intersection of atmospheric science, power systems, and machine learning—combining mechanistic, physics-based understanding of infrastructure failure with data-driven probabilistic methods. Your models will feed real-time operational products used by utilities to anticipate outages, position crews, and manage grid risk during storms, extreme winds, and wildfire conditions.

Responsibilities

• Design, develop, and validate machine learning models to predict transmission outages driven by extreme weather, combining mechanistic and probabilistic approaches.
• Build spatio-temporal models that link weather forecasts to infrastructure failure risk, including probability of failure (POF) estimates for transmission and distribution assets.
• Develop models characterizing the interrelationship between transmission outages, extreme weather events, and wildfire ignition risk.
• Integrate heterogeneous datasets—weather model output, asset and infrastructure data, historical outage records, and geospatial layers—into robust, reproducible modeling pipelines.
• Operationalize research-grade models into fast, reliable production systems suitable for real-time forecasting workflows.
• Evaluate and benchmark model performance against state-of-the-art methods and clearly communicate accuracy, skill, and uncertainty to internal teams and utility customers.
• Collaborate with meteorologists, risk modelers, and software engineers to improve Technosylva’s outage and extreme weather product capabilities.
• Leverage agentic coding tools throughout the development lifecycle—using AI agents to accelerate model prototyping, pipeline development, testing, and documentation—while maintaining rigorous review and validation standards.

Qualifications

• Ph.D. in Environmental Engineering, Atmospheric Science, Civil Engineering, Statistics, Data Science, or a related quantitative field strongly preferred.
• A master’s degree with substantial applied experience in weather-driven outage or infrastructure risk modeling will be considered.

Requirements

• Demonstrated experience developing transmission outage prediction models—this is a core requirement for the role.
• 5+ years of experience (academic or industry) applying statistical modeling and machine learning to grid reliability, storm outage prediction, or related energy-sector problems.
• Experience working with utilities, ISOs/RTOs, or grid operators on weather-related operational forecasting is highly valued.
• Track record of peer-reviewed publications, patents, or deployed production models in outage prediction, wildfire risk, or extreme weather impacts.
• Strong grounding in machine learning methods (ensemble methods, neural networks, probabilistic models) and statistical modeling for spatio-temporal problems.
• Experience combining physics-based/mechanistic models with data-driven approaches for infrastructure failure prediction.
• Proficiency with geospatial data and tools (GeoPandas, ArcGIS or equivalent) and large multidimensional weather datasets.
• Advanced Python skills (NumPy, Pandas, Scikit-learn, TensorFlow or PyTorch) with the ability to write clean, well-documented, production-quality code; experience with R, SQL, or Julia is a plus.
• Ability to optimize model runtime and computational workflows for real-time operational use.
• Hands-on experience using agentic coding tools (Claude Code, Cursor, Copilot agents, or similar) as a core part of daily development workflows—not just autocomplete, but delegating multi-step coding tasks to AI agents.
• Skilled at structuring work for AI agents: writing clear specifications, decomposing problems, and providing context so agents produce correct, maintainable code.
• Strong judgment in reviewing and validating agent-generated code, especially for scientific correctness in modeling pipelines.