Energy Systems Data Scientist

Overview

COMPANY OVERVIEW

Pattern Energy is a leading renewable energy company that develops, constructs, owns, and operates high-quality wind and solar generation, transmission, green fuels and energy storage facilities. Our mission is to transition the world to renewable energy through the sustainable development and responsible operation of facilities with respect for the environment, communities, and cultures where we have a presence. 

 

Our approach begins and ends with establishing trust, accountability, and transparency. Our company values of creative spirit, pride of ownership, follow-through, and a team-first attitude drive us to pursue our mission every day. Our culture supports our values by fostering innovative and critical thinking and a deep belief in living up to our promises.  Headquartered in San Francisco, Pattern has a portfolio of 30 power facilities and transmission assets across North America, serving various customers that provide low-cost clean energy to millions of consumers. 

Responsibilities

JOB PURPOSE

The Energy Systems Data Scientist role develops, maintains, and analyzes the input, output and connection datasets between Pattern’s internal capacity expansion and production cost modeling suite (WIS:dom). The role will evolve in scope as the data architecture and stack progress from its current state. The role will enable ESP to analyze North American energy markets and develops a comprehensive view of the current Pattern pipeline of construction, operating asset performance, and market dynamics that might create opportunities or risks. The role will provides critical support for ESP to provide business actionable analysis to other departments of Pattern.

 

KEY ACCOUNTABILITIES

• Create, manage, and analyze input and output data for/from executed model simulations using the WIS:dom suite of tools. Provide analysis of these inputs and outputs to the ESP team and external groups.
• Integrate large datasets into the modeling framework. Gather and validate input data for models, including energy demand, resource availability, market trends, and environmental constraints. Find available market data and translate data into modeling WIS:dom parameters and maintain version control and documentation of changes.
• Automate repetitive tasks and enhance existing workflows to improve input and output data for modeling accuracy and efficiency.
• Develop pipeline infrastructure between modeling tools that will reduce the manual nature of model execution in coordination with the transition to the HIVE
• Work with multidisciplinary teams, including modelers, developers, analysts, GIS, and transmission analysts to align model data requirements that simulate real-world conditions and objectives.
• Assist real-time environment products for operations that uses different data structures to other ESP modeling tools.

Qualifications

EXPERIENCE/QUALIFICATIONS/EDUCATION REQUIRED

 

Educational Requirements

Bachelor’s and/or master’s in electrical engineering, economics, mathematics, or a related quantitative field (data science or data engineering emphasis desired).

 

Required Work Experience

3-5 years of experience in energy trading, renewables development or energy industry forecasting/analytics/research.

 

Required Knowledge

• Familiarity with capacity expansion, production cost models, or energy-related software.
• Ability to work with datasets specific to energy systems, such as grid network models, load profiles, and pricing data. Strong knowledge of data wrangling and cleaning techniques, especially for time series, spatial, and network data.
• Excellent programming skills in common languages (e.g., Python) and packages used by energy modeling field (e.g., geopandas, numpy, networkx, pandas), use of software best practices (e.g., Git), and familiarity with high performance computing environments.
• Experience with extracting, transforming, and loading processes and tools for handling large-scale datasets. Demonstrated ability to develop and deploy Feature Engineering and Modeling applications to data platforms built on Databricks or similar platforms and platform components (e.g., Snowflake, ML Flow, Airflow, etc.)
• Demonstrated experience in using Azure-based cloud applications, services and infrastructure or significant, transferrable experience with other Cloud Providers (e.g., AWS or GCP)
• Comfortable creating data visualizations and deploying them on a company-wide level.
• Implementation of storing system-level logs and responding to pipeline failures (including code errors, API statuses, data structure failures, and machine-based