← Back to all jobs

GE Vernova GridOS Project Engineer - Co-Op/Intern - January 2027-June 2027

GE Vernova · Bellevue + 1 more · Posted 2026-08-20

Apply on the company site →

Job description

Job Description Summary GridOS Project Engineer Co-Op/Intern Addressing the climate crisis is an urgent global priority, and at GE Vernova, we take our responsibility seriously. That is the singular mission of GE Vernova: to continue electrifying the world while simultaneously working to help decarbonize it. Innovation Are you passionate about innovation? Are you excited at the opportunity to electrify and decarbonize the world? We operate with a founder’s mindset. We deliver innovation with passion, speed, and courage. We continuously challenge our thinking and are empowered to dream big and take smart risks. Job Description InnovationAre you passionate about innovation? Are you excited at the opportunity to electrify and decarbonize the world? We operate with a founder’s mindset. We deliver innovation with passion, speed, and courage. We continuously challenge our thinking and are empowered to dream big and take smart risks. GE Vernova is seeking a highly motivated graduate student intern to help advance the use of Artificial Intelligence and Large Language Models (LLMs) in electric utility network model validation, diagnostics, and automated remediation.This co-op/internship focuses on applying AI/LLM technologies to analyze large-scale power system model validation and diagnostic data, identify model quality issues, determine root causes, and recommend corrective actions across utility enterprise systems. The work will contribute to the next generation of intelligent model management solutions used by electric utilities worldwide.The ideal candidate combines strong knowledge of electric power systems with practical experience using AI/LLMs for data analysis, reasoning, and automation. Candidates with a Power Systems or Computer Science background is a must.Employment Dates: January 2027 - June 2027 or up to 12 months Roles and Responsibilities: • Analyze extensive power system model validation and diagnostic logs. • Develop AI/LLM-based approaches to detect, classify, and prioritize modeling issues. • Investigate network model inconsistencies and determine probable root causes. • Build intelligent workflows that prescribe suggestive or corrective actions for model remediation. • Support and Perform analysis, troubleshooting, and support of key Distribution Automation functions—including power flow analysis, fault isolation and service restoration (FLISR), Volt-VAR optimization (VVO), fault location, and feeder reconfiguration. Collaborate with Engineering teams and end customers to ensure reliable, effective, and sustained operation of these advanced distribution capabilities. May own a subset of a project and be responsible for integrating, configuring, and testing this piece of the project, which contributes to the overall solution. • Works with other internal delivery teams to obtain fixes on a timely basis to support maintaining the project schedule. Assists with tracking resolutions to issues and creates detailed documentation of solutions implemented and troubleshooting guides. • Develop automated reasoning frameworks that can operate across multiple utility domains, including: • GIS (Geographic Information Systems) • SCADA/EMS systems • Customer Information Systems • Planning and Engineering applications • Design prompt engineering, retrieval, agentic, or workflow-based solutions using modern LLM technologies. • Evaluate AI-generated recommendations for accuracy, explainability, and operational value. • Collaborate with software engineers, architects, and power system experts to prototype and validate solutions. • Under general supervision, works to identify system problems and failures. Pursues solutions to system problems by researching issue and obtaining support from both internal and external resources. • Document research findings and present results to engineering leadership. This is a 6-12 month internship (12 months preferred) and offers an opportunity to work on cutting-edge AI solutions that improve the quality, reliability, and maintainability of power system network models. Exceptional candidates may be considered for future full-time opportunities within GE Vernova. Required Qualifications: • B.S or M.S. Electrical Engineering (Power Systems specialization) or Computer Science . • Strong analytical and problem-solving skills. • Programming experience in Python and data analytics. • Excellent English communication skills – both written and oral Other Eligibility Requirements:• The required work location is Bellevue, WA or Atlanta, GA - Hybrid ( 2 days in office and 3 days remote)• Must have the ability to work in the United States for an unlimited amount of time without sponsorshipPreferred Qualifications: • Experience with AI, Machine Learning, Generative AI, or Large Language Model • Interest in applying AI to power system modeling/ application, validation, and automation. • Good knowledge of Windows, .NET, SQL databases, Web technology integration, (i.e. – Web Servers and Web Services) and SOA technologies • Active perticipation in University project in software design, software integration and/or Power System related experience. • Minimum 3.0 on a 4.0 scale or 4.0 on a 5.0 scale cumulative GPA (without rounding) Benefits Available to You: Addressing the climate crisis is an urgent global priority, and at GE Vernova, we take our responsibility seriously. That is the singular mission of GE Vernova: to continue electrifying the world while simultaneously working to help decarbonize it. In order to meet this mission, we provide varied, competitive benefits to help support our workforce. The pay range for this position is $1,000-$2,000 USD weekly. The specific pay offered may be influenced by a variety of factors, including the candidate’s experience, education, and skill set. This position is also eligible for: Relocation Assistance: Co-op/Interns will be reimbursed for reasonable, proper, and documented expenditures incurred while initially reporting to work and