Requisition ID # 158644
Job Category: Accounting / Finance
Job Level: Individual Contributor
Business Unit: Information Technology
Work Type: Hybrid
Job Location: Oakland
Department Overview
The Data Science & Decision Science Department is both a “Delivery” team that is a sophisticated practitioner of data science and a “Center of Excellence” team that supports other practitioners in an enterprise-wide Hub & Spoke analytics adoption model.
As a Delivery team, this Department uses industry leading data science and change management practices to drive PG&E’s transition to the sustainable grid of the future. The Department works cross-functionally across the company to enable data driven decisions applying analytics, as well as improvements to relevant business processes. Deployed to some of PG&E’s highest priority arenas, the Department does not specialize in a traditional utility domain, such as asset management or program administration, but instead specializes in extracting useful insights from disparate data sets and facilitating actions informed by these insights.
As a Center of Excellence team, this Department listens to the needs of practitioners across the company, along with emerging industry practices, and builds standards, processes, tools, knowledge and best practices that meet the current and future needs of the enterprise.
This team works on a wide variety of difficult problems, offering great variety in the work, and constant opportunity to explore and learn. Current and past engagements include:
Creating wildfire risk models that are used by regulators and the utility to prioritize asset management.
Developing computer vision models that improve, accelerate, and automate asset inspections processes.
Predicting electric distribution equipment failure before it occurs, allowing for proactive maintenance.
Forming the analytical framework behind PG&E’s Transmission Public Safety Power Shutoff
Optimizing non-wires alternative resource portfolios, like the Oakland Clean Energy Initiative, including location and resource adequacy considerations.
Analyzing customer demographic, program participation, and SmartMeter interval data to build program targeted propensity models, e.g. for customer owned distributed energy resource technologies.
Identifying and investigating anomalous customer natural gas usage, in order to resolve dangerous customer side leaks.
Position Summary
PG&E is looking for a Data Scientist with experience in data science products and ML DevOps. In this role the successful candidates will play a vital role in building and maintaining the infrastructure that brings our machine learning models to life, having the opportunity to advance PG&E’s triple bottom line of People, Planet, and Prosperity. Working as part of cross functional teams, including with data scientists, ML engineers, and software engineers to ensure seamless integration and deployment of models into production environment. The responsibilities of these positions include:
As Center of Excellence team member in the centralized data science Hub, support analytics Spokes across the company in the implementation of the ML DevOps Framework for their productionalize models.
Assist in developing and documenting the standards ML DevOps pipelines for training, testing, deployment, and monitoring of machine learning models.
Collaborate with data scientists and ML engineers to understand model requirements and translate them into production-ready pipelines.
Participate in the design and implementation of CI/CD pipelines for machine learning models.
Participate in code reviews and contribute to the improvement of existing ML DevOps tools.
Monitor model performance in production and identify potential issues.
Assist in troubleshooting and resolving issues related to model deployments.
Stay up to date on the latest ML DevOps trends and technologies.
Participate in the design, development, and testing of ML DevOps pipelines.
Write and maintain well-documented, efficient, and scalable ML DevOps code.
Build and maintain strong relationships with business units and external agencies.
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. We would not anticipate that the individual hired into this role would land at or near the top half of the range described below, but the decision will be dependent on the facts and circumstances of each case.
A reasonable salary range is:
Bay Area : $102,000.00
Bay Area : $162,000.00
&/OR
California : $97,000.00
California : $154,000.00
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.
Reporting Relationship
This position reports to the Director, Enterprise Decision Science/Data Science & Analytics Products.
Job Responsibilities:
Develop and document the standards ML DevOps pipelines for training, testing, deployment, and monitoring of machine learning models.
Extracts, transforms, and loads data from dissimilar sources from across PG&E for their machine learning feature engineering.
Supports the application of data science/ machine learning/artificial intelligence methods to develop defensible and reproducible predictive or optimization models.
Supports and implement the ML model governance and monitoring of model performance in production.
Supports the development of mathematical models and AI simulations which represent complex business problems.
Writes and documents python code for data science (feature engineering and machine learning modeling), and ML DevOps under senior data scientist guidance.
Contributes to the development of summary presentations.
Communicates technical information clearly to other data scientists.
Qualifications:
:
Bachelor’s Degree in Data Science, Machine Learning, Computer Science, Physics, Econometrics or Economics, Engineering, Mathematics, Applied Sciences, Statistics, or equivalent field
2 years in data science (or no experience, if possess Master’s Degree)
Desired:
Master’s Degree in Data Science, Machine Learning, Computer Science, Physics, Econometrics or Economics, Engineering, Mathematics, Applied Sciences, Statistics, or equivalent field
Relevant industry (electric or gas utility, renewable energy, analytics consulting, etc.) experience
Knowledge, Skills, Abilities and (Technical) Competencies
Familiarity with data science and ML DevOps standards and processes (model evaluation, optimization, feature engineering, model deployment, monitoring etc.) along with best practices to implement them.
Knowledge of software engineering, statistics, and machine learning techniques as they apply to data science modeling and deployment.
Knowledge of commonly used data science and/or operations research programming languages, packages, and tools.
Hands-on knowledge and application of data science/machine learning models and algorithms.
Ability to clearly communicate complex technical details and insights to colleagues and stakeholders.
Knowledge of the mathematical and statistical fields that underpin data science.
Knowledge of systems thinking and structuring complex problems.
Ability to collaborate and/or work on a team.
