Principal Data Scientist

Role Overview

The Undergrounding Risk Management group within Undergrounding & System Hardening works to strengthen risk management practices for Electric Operations and help the organization respond to changing external pressures, including climate-related impacts. The Electric Risk Management & Analytics team builds, maintains, and applies predictive models that narrow the gap between performance metrics and actual electric system behavior. These models give the business a layered view of system risk and risk reduction so employees across the company can make better-informed decisions.

What You’ll Work On

• Measure how wildfire mitigation programs are performing across distribution and transmission systems.
• Build predictive models in Python or PySpark and run them in Foundry or AWS.
• Analyze and incorporate meteorological inputs alongside asset, vegetation, and other utility data into models.
• Design statistical approaches and build programmatic solutions that turn risk model outputs into practical business tools.
• Develop scripts, programs, models, user interfaces, algorithms, and workflows that handle both structured and unstructured data from multiple sources.
• Create defensible, scalable, reproducible, and well-documented machine learning and AI models for prediction or optimization.
• Help non-technical stakeholders understand what data science solutions can do, where their limits are, and how mature they are.
• Apply advanced data science methods to support business decisions and identify patterns in complex datasets.
• Build data mining structures, statistical reporting, and analytical methods to surface trends in mixed data.
• Extract, transform, and load data from varied sources for feature engineering and model development.
• Prepare and wrangle data for machine learning pipelines.
• Develop reusable functions and modular code for data science work.
• Evaluate how modeling choices, inputs, implementation details, and analytical processes affect business outcomes.
• Partner with stakeholders and subject matter experts to identify useful data science opportunities.
• Present conclusions and recommendations to senior leadership.
• Serve as a peer reviewer for complex models.

Required Background

• Master’s degree in Data Science, Machine Learning, Computer Science, Civil Engineering, Mechanical Engineering, Electrical Engineering, Statistics, or a closely related field.
• At least 8 years of experience in data science; or 2 years of experience if you hold a doctoral degree or higher in one of the listed fields.

Preferred Qualifications

• Doctorate degree in Data Science, Machine Learning, Computer Science, Civil Engineering, Mechanical Engineering, Electrical Engineering, Statistics, or a related discipline.
• Strong ability in experimental design and causal inference.
• Deep knowledge of time series analysis, statistical modeling, and probabilistic risk assessment.
• Experience in utility, energy, or data science consulting environments.
• Understanding of supervised, unsupervised, deep learning, and physics-based approaches for electrical infrastructure failure modeling.
• Solid command of data science best practices such as model evaluation, optimization, and feature engineering.
• Awareness of current industry developments shown through journal publications, conference talks, open-source work, or similar contributions.
• Comfort working with Agile product development practices.
• Strong Python or PySpark development skills, including code reviews and disciplined coding practices.
• Ability to explain statistical inference, machine learning concepts, software engineering topics, and deployment pipelines in depth.
• Excellent communication skills for translating technical work to colleagues and stakeholders.
• Capability to coach, mentor, and support the development of others.

Additional Information

Top priorities for this role include PySpark proficiency, user interface development experience, and strong cross-functional collaboration skills.

Location: Oakland, CA.

This is a contract position based onsite.

No stipend or salary amount was provided in the source.