Expert Data Scientist - Transmission Right of Way (ROW) Risk Analytics

PG&E; Oakland (CA); Hybrid; USD 140,000 - 238,000; Full time

Job summary

PG&E is seeking a highly analytical Data Scientist to advance a quantitative risk analysis and predictive analytics capability for Transmission Right of Way risk reduction. You will design data-driven methods to quantify risk, prioritize encroachments, and predict safety and reliability events.

You will partner with cross-functional teams to translate field and asset data into actionable insights, building models for proactive decision-making and improved grid reliability.

Qualifications

• Bachelor's degree in Data Science, Statistics, Applied Mathematics, Engineering, CS, Economics, or related field.
• At least 6 years of experience in data science, predictive analytics, or statistical modeling.

Responsibilities

• Quantitative Risk Modeling: develop risk frameworks and scoring methodologies to estimate likelihood and consequence of events.
• Predictive Analytics & Machine Learning: build models using statistical and ML techniques; identify risk drivers.
• Data Integration & Analytical Pipeline Development: aggregate and clean data from multiple systems; build repeatable pipelines.
• Decision Support & Program Prioritization: translate model outputs into prioritization tools; support planning and investments.
• Monitoring, Validation & Continuous Improvement: track model performance; calibrate and refine methods.
• Cross-Functional Collaboration: work with operations, risk, IT, GIS, and leadership to align analytics with business needs.

Skills

Data science

Predictive analytics

Statistical modeling

Machine learning

Python

R

SQL

Data visualization

Communication

Education

Bachelor's degree

Tools

Power BI

Tableau

Geospatial tools

Job description

Job Category: Accounting / Finance

Job Level: Individual Contributor

Business Unit: Energy Delivery

Work Type: Hybrid

Job Location: Oakland; Alameda; Alta; American Canyon; Angels Camp; Antioch; Auberry; Auburn; Avenal; Avila Beach; Bakersfield; Balch Camp; Bay Point; Bear Valley; Belden; Bellota; Belmont; Benicia; Berkeley; Brentwood; Brisbane; Buellton; Burney; Buttonwillow; Calistoga; Campbell; Canyon Dam; Canyondam; Capitola; Caruthers; Chico; Clearlake; Clovis; Coalinga; Colusa; Concord; Concord; Corcoran; Cotati; Cottonwood; Cupertino; Daly City; Danville; Davis; Dinuba; Downieville; Dublin; Emeryville; Eureka; Fairfield; Folsom; Fort Bragg; Fortuna; Fremont; French Camp; Fresno; Fresno; Fulton; Garberville; Geyserville; Gilroy; Goodyear; Grass Valley; Guerneville; Half Moon Bay; Hayward; Hinkley; Hollister; Holt; Huron; Jackson; Kerman; King City; Lakeport; Lemoore; Lincoln; Linden; Livermore; Lodi; Loomis; Los Banos; Lower Lake; Madera; Magalia; Manteca; Manton; Mariposa; Martell; Marysville; Maxwell; Menlo Park; Merced; Meridian; Millbrae; Milpitas; Modesto; Monterey; Montgomery Creek; Morgan Hill; Morro Bay; Moss Landing; Mountain View; Napa; Needles; Newark; Newman; Novato; Oakdale; Oakhurst; Oakley; Olema; Orinda; Orland; Oroville; Palo Alto; Palo Cedro; Paradise; Parkwood; Paso Robles; Petaluma; Pioneer; Pismo Beach; Pittsburg; Placerville; Pleasant Hill; Pleasanton; Point Arena; Potter Valley; Quincy; Rancho Cordova; Red Bluff; Redding; Richmond; Ridgecrest; Rio Vista; Rocklin; Roseville; Round Mountain; Sacramento; Salida; Salinas; San Bruno; San Carlos; San Francisco; San Francisco; San Jose; San Luis Obispo; San Mateo; San Rafael; San Ramon; San Ramon; Sanger; Santa Cruz; Santa Maria; Santa Nella; Santa Rosa; Selma; Shaver Lake; Sonoma; Sonora; South San Francisco; Springville; Stockton; Storrie; Taft; Tracy; Turlock; Twain; Ukiah; Vacaville; Vallejo; Walnut Creek; Wasco; Watsonville; West Sacramento; Wheatland; Whitmore; Willits; Willow Creek; Willows; Windsor; Winters; Woodland; Yuba City

Department Overview

The Right-of-Way Risk Reduction Strategy (ROWRS) team within Electric Transmission Engineering establishes a risk-based, technology-enabled approach to identify, prioritize, and resolve electric right-of-way encroachments and clearance issues. The team partners across Electric Operations, Land, Legal, Wildfire Risk, IT, Data and Analytics, and other functions to improve risk visibility, standardize processes, and support sustained reduction of right-of-way risk across PG&E's service territory.

Position Summary

We are seeking a highly analytical and mission-driven Data Scientist to support the development of a quantitative risk analysis and predictive analytics capability for Transmission Right of Way (ROW) Risk Reduction Strategy. This role will help design and operationalize data-driven methods to quantify risk, prioritize encroachments, and predict the likelihood of safety and reliability events associated with transmission right of way encroachments.

The successful candidate will partner with cross-functional teams across electric operations, asset management, vegetation management, engineering, risk, compliance, GIS, inspection, and program management to translate field, asset, and operational data into actionable insights. The Data Scientist will build models that enable proactive decision-making by identifying where encroachments pose the greatest potential threat to public safety, worker safety, grid reliability, asset integrity, and wildfire risk.

This role is ideal for someone who combines deep technical expertise in statistical modeling and machine learning with the ability to work in complex operational environments and communicate insights to business and executive stakeholders.

This position is hybrid, working from your remote office and your assigned location at least two days a week and or based on business need.

Bay Area Minimum: $140,000

Bay Area Mid: $189,000
Bay Area Maximum: $238,000

California Minimum: $133,000

California Mid: $180,000

California Maximum: $226,000

This job is also eligible to participate in PG&E's discretionary incentive compensation programs.

Job Responsibilities

Quantitative Risk Modeling

• Develop quantitative risk frameworks to assess the risk posed by encroachments within or adjacent to transmission rights of way.
• Define risk equations, scoring methodologies, and analytical models that estimate both:
  • Likelihood of an event occurring (e.g., safety incident, reliability event, asset damage, access impairment, wildfire ignition, clearance violation, line contact, third-party interference), and
  • Consequence / impact of that event.
• Incorporate multiple risk dimensions into a unified analytical framework, including:
  • Public and employee safety
  • Electric reliability / outage exposure
  • Wildfire and ignition risk
  • Regulatory and compliance exposure
  • Asset damage and access limitations
  • Financial and operational impact

Predictive Analytics & Machine Learning

• Build predictive models to estimate the likelihood of future safety or reliability events resulting from existing or emerging encroachments in transmission rights of way.
• Apply statistical and machine learning techniques such as:
  • Logistic regression
  • Survival analysis / time-to-event modeling
  • Random forests / gradient boosting
  • Bayesian methods
  • Scenario modeling and simulation
  • Geospatial and spatiotemporal modeling
• Identify leading indicators and risk drivers that increase the probability of an event, such as:
  • Proximity to energized assets
  • Encroachment type and severity
  • Clearance deficits
  • Structure condition / asset age
  • Land use and development patterns
  • Historical incident patterns
  • Inspection findings
  • Environmental and weather conditions
  • Access constraints
  • High Fire Threat District (HFTD) or other high-risk locations

Data Integration & Analytical Pipeline Development

• Aggregate, clean, and structure data from multiple enterprise and operational systems, including GIS, asset management, inspections, outage history, incident data, vegetation data, work management, and field observations.
• Develop repeatable analytical pipelines to support risk scoring, trend analysis, forecasting, and prioritization.
• Assess data quality, completeness, and lineage; identify data gaps and recommend improvements to enable stronger analytics.
• Partner with IT, data engineering, GIS, and business teams to improve data architecture and enable scalable model deployment.

Decision Support & Program Prioritization

• Translate model outputs into practical prioritization tools that support program strategy, annual planning, and execution.
• Develop dashboards, visualizations, and decision-support tools to help the business:
  • Rank encroachments by risk
  • Identify high-priority mitigation opportunities
  • Forecast emerging risk hotspots
  • Evaluate tradeoffs across mitigation options
  • Support resource allocation and investment decisions
• Support the development of business cases and analytical narratives for leadership, regulators, and governance forums.

Monitoring, Validation & Continuous Improvement

• Establish model validation, calibration, and performance monitoring processes to ensure analytics remain accurate, explainable, and fit for purpose.
• Track model precision, recall, false positives/negatives, drift, and operational usefulness over time.
• Conduct sensitivity analyses, scenario testing, and back-testing against historical events.
• Continuously improve methodologies as new data sources, field intelligence, and business requirements emerge.

Cross-Functional Collaboration

• Partner closely with subject matter experts in transmission operations, inspection, engineering, wildfire mitigation, risk management, land/ROW, and compliance to ensure models reflect real-world operating conditions.
• Facilitate discussions to define risk taxonomy, modeling assumptions, thresholds, and action triggers.
• Communicate technical findings clearly to both technical and non-technical stakeholders, including senior leadership.

Qualifications

Minimum

• Bachelor's degree in Data Science, Statistics, Applied Mathematics, Engineering, Computer Science, Operations Research, Economics, or a related quantitative field.
• 6 of experience in data science, predictive analytics, quantitative risk analysis, or statistical modeling.

Desired

• Master's or PhD in a quantitative discipline.
• Experience building predictive models using Python, R, SQL, or similar tools.
• Experience working with large, complex, and imperfect datasets from multiple business systems.
• Ability to explain technical results to operational and executive audiences in a clear, concise, and decision-oriented manner.
• Demonstrated ability to turn ambiguous business problems into structured analytical approaches.
• Experience in electric utility, transmission operations, wildfire risk, asset risk management, infrastructure risk, public safety risk, or reliability analytics.
• Experience with geospatial analytics, including GIS-based risk modeling.
• Familiarity with transmission asset data, ROW management, encroachment data, inspection data, outage/event history, or utility asset health data.
• Experience in regulated industries where transparency, traceability, and model explainability are essential.
• Knowledge of safety and reliability risk concepts in utility operations.
• Experience developing dashboards or decision-support tools using Power BI, Tableau, or similar platforms.
• Familiarity with cloud analytics environments and productionizing models for business use
• Strong problem-solving and structured thinking
• Ability to work across technical and operational disciplines
• High attention to detail and analytical rigor
• Strong business acumen and decision orientation
• Comfort working in evolving, ambiguous problem spaces
• Ability to balance model sophistication with usability and explainability
• Excellent written and verbal communication skills
• Programming:Python, R, SQL
• Analytics: Statistical modeling, machine learning, forecasting, simulation, optimization
• Data tools: Data wrangling, ETL concepts, data quality assessment
• Visualization: Power BI, Tableau, matplotlib, seaborn, or similar
• Geospatial: ArcGIS, QGIS, GeoPandas, spatial analysis techniques
• Strong knowledge of statistical inference,machine learning,risk modeling,forecasting, feature engineering, data wranging and data quality management
• Modeling concepts:
  • Classification and probability prediction
  • Risk scoring frameworks
  • Time-to-event / hazard models
  • Explainable AI / interpretable models
  • Scenario analysis and Monte Carlo methods