Department Overview
The aim of the Data Solutions team in the Wildfire Mitigation organization is to enhance the risk practices of PG&E's Electric Operation business and thereby address changing external conditions such as climate change. To this end, the Data Solutions team enhances and maintains predictive models of electric system failures. These models help to provide a multi-layered view of risk across the electric system so that decision-making processes include and empower employees at all levels of the company to manage risk appropriately.
Sample activities include:
- Development of new Machine Learning (ML) models characterizing and predicting distribution and transmission electric system environmental conditions using remote sensing data.
- Development of end-to-end solutions that take satellite imagery and derived products and transform them into analysis-ready insights, cloud-optimized datasets accessible within distributed Spark environments.
- Support for stakeholders in how to integrate remote-sensing based features into downstream analysis and risk models.
Position Summary
Designs, develops, and executes scripts, programs, models, algorithms, and processes, using structured, unstructured, and geospatial data from disparate sources and sizes, generating defensible, valid, scalable, reproducible, and documented machine learning and artificial intelligence models (predictive or optimization) for problem-solving and strategy development. Participates in internal and external communities of practice in data science/artificial intelligence/machine learning to advance knowledge in the field. Educates the non-technical community on the advantages, risks, and maturity levels of data science solutions.
This position is hybrid, working from your remote office and your assigned work location based on business need. The assigned work location will be within the PG&E Service Territory.
PG&E is providing the salary range that the company in good faith believes it might pay for this position at the time of the job posting. This compensation range is specific to the locality of the job. The actual salary paid to an individual will be based on multiple factors, including, but not limited to, specific skills, education, licenses or certifications, experience, market value, geographic location, and internal equity. Although we estimate the successful candidate hired into this role will be placed towards the middle or entry point of the range, the decision will be made on a case-by-case basis related to these factors.
Bay Minimum: $140,000 Bay Maximum: $238,000
&/OR
CA Minimum: $133,000 CA Maximum: $226,000
This job is also eligible to participate in PG&E's discretionary incentive compensation programs.
Job Responsibilities
- Applies strong foundations of remote sensing and advanced techniques in image analysis, geospatial analytics, machine learning, and deep learning to extract insights from complex imagery datasets (e.g., multispectral, lidar, SAR).
- Designs and develops production-quality spatial algorithms to extract, validate, and enrich features from remote sensing, derived imagery, and enterprise geospatial datasets.
- Builds and operates scalable, cloud-native geospatial and ML pipelines for imagery ingestion, preprocessing, feature engineering, and delivery of production-ready outputs across large spatiotemporal datasets.
- Engineers and optimizes cloud-based geospatial and ML workflows using distributed processing frameworks to balance performance, cost, and reliability for batch and large-scale workloads.
- Develops and maintains reusable, well-documented Python geospatial codebases and data catalogs, leveraging cloud-optimized formats and STAC-compliant architectures to ensure efficient access, processing, and reproducibility.
- Researches and applies advanced knowledge of existing and emerging geospatial data science principles, theories, and techniques to inform business decisions.
- Creates advanced data mining architectures/models/protocols, statistical reporting, and data analysis methodologies to identify trends in structured and unstructured data sets.
- Extracts, transforms, and loads data from dissimilar sources from across PG&E for machine learning feature engineering.
- Applies data science/machine learning/artificial intelligence methods to develop defensible and reproducible predictive or optimization models that involve multiple facets and iterations in algorithm development.
- Wrangling and prepares data as input for machine learning model development and feature engineering.
- Writes and documents reusable Python functions and modular Python code for data science.
- Assesses business implications associated with modeling assumptions, inputs, methodologies, technical implementation, analytic procedures and processes, and advanced data analysis.
- Works with sponsor departments and company subject matter experts to understand the application and potential of data science solutions that create value.
- Presents findings and makes recommendations to senior management.
- Acts as a peer reviewer of complex models.
Qualifications
Minimum:
- Bachelor's Degree in Data Science, Machine Learning, Computer Science, Physics, Econometrics or Economics, Engineering, Mathematics, Applied Sciences, Statistics, or equivalent field.
- 6 years in data science OR no experience, if possessing a Doctoral Degree or higher, as described above.
Desired:
- Doctorate Degree in Data Science, Machine Learning, or job-related discipline or equivalent experience.
- Relevant industry (electric or gas utility, renewable energy, analytics consulting, etc.) experience.
- 4 years of Python programming experience.
- Proven experience and working knowledge of geospatial and remote sensing imagery data, with a focus on vegetation and environmental data.
- Proven experience with methods and tools of geospatial data processing.
- Experience writing software to extract features from remote sensing imagery data, time-series, or large-scale vector and raster datasets.
- Familiarity with cloud computing platforms and distributed processing frameworks to support geospatial and remote sensing scalable analytics.
- Experience with foundation models, machine learning, or computer vision to transform imagery into intelligence.
- Active participation in the external geospatial data science/artificial intelligence/machine learning community through publications, conferences, or open-source contributions.
- Competency with data science standards and best practices (model evaluation, feature engineering, reproducibility, deployment pipelines).
- Competency with commonly used data science and/or operations research programming languages, packages, and tools for building data science/machine learning models and algorithms.
- Proficiency in explaining complex technical concepts across geospatial analytics, machine learning, and data engineering to both technical and non-technical audiences.
- Strong communication skills and ability to mentor and develop others.