叶片 - 数字工程与人工智能专家

Envision Energy's Global Blade Innovation Center (GBIC) was established in 2015 to build a world-class, in-house blade design capability. Engineers from industry-leading OEMs, national laboratories, and top graduate programs have collaborated to create a state-of-the-art design capability from the ground up. Envision's in-house blade designs and technologies have disrupted global markets and delivered significant reductions in Levelized Cost of Energy (LCOE) alongside measurable expansion of Envision's market share.

The wind industry is at an inflection point in how engineering work gets done. GBIC is investing in the AI and digital engineering capabilities needed to stay at the leading edge, and this role is the architect of that effort.

The Role

This role is for an engineer who builds. Not a software developer who has learned engineering terminology, but someone who has worked inside complex engineering workflows, understood where they break down, and developed the technical skills to fix them through software, simulation automation, and applied AI.

As the Digital Engineering & AI Specialist, you will define, own, and execute the architecture of digital tools and AI systems that transform how the Blade Design team operates. Your starting point is always the engineering problem: what slows design iteration, what makes failure analysis manual and slow, where manual variability in manufacturing processes introduces quality risk that better tooling could detect or prevent, what keeps institutional knowledge locked in individual heads. From that understanding, you will build tools that make the team faster, more consistent, and capable of solving problems at a scale not otherwise possible.

The AI and software capabilities you bring are in service of the engineering. That distinction shapes everything about how this role is defined and how success is measured.

Key Responsibilities

Engineering Workflow Automation & Tool Development

• Identify, design, and build digital tools that eliminate high-friction, manual steps in blade design, analysis, and field reliability workflows, including simulation pre/post-processing automation, inspection data pipelines, analysis reporting, and parametric design tools.
• Develop and maintain internal engineering software platforms, APIs, and scripting infrastructure that integrate directly into engineering toolchains (FEA, CAD, CFD, and data environments).
• Build automation pipelines that connect simulation outputs, manufacturing data, and field performance records into structured, queryable engineering knowledge bases.
• Collaborate with blade design, structural analysis, and field reliability engineers to understand workflow friction firsthand before building solutions for it.

AI/ML for Engineering Applications

• Develop and deploy AI/ML models grounded in physical engineering understanding, including surrogate models for structural performance, defect detection and classification from inspection data, failure mode prediction, and manufacturing quality assessment.
• Apply physics-informed modeling approaches where engineering domain knowledge can improve model reliability, generalizability, and trustworthiness.
• Design and deploy agentic AI systems and multi-agent workflows that automate complex, multi-step engineering tasks such as inspection processing, RCA support, and design evaluation.
• Validate all AI/ML outputs rigorously against physical test data, field evidence, and engineering first principles. Model confidence must be earned through engineering validation, not assumed from training metrics.
• Establish standards for AI-assisted engineering work products, ensuring outputs are traceable, auditable, and held to the same quality bar as conventional engineering analysis.

Simulation Integration & Computational Design

• Develop tools and workflows that bridge CAD, FEA, and CFD environments, enabling automated model generation, parametric design exploration, and systematic result extraction.
• Build surrogate models and reduced-order modeling frameworks that accelerate design iteration without sacrificing physical fidelity.
• Support the development of digital twin concepts for blade structural performance, connecting simulation models to field data and in-service measurements.
• Automate simulation data pipelines from setup through post-processing, making high-fidelity analysis faster and more repeatable across the team.

Technical Leadership & Domain Collaboration

• Work closely with composite design and field reliability engineers to understand physical failure modes and translate that knowledge into effective tool architecture, model features, and validation strategies.
• Communicate tool capabilities, limitations, and outputs clearly to engineering stakeholders. Earning trust through transparent, physically grounded outputs is as important as technical performance.
• Stay current with advances in engineering software, applied AI for structural and manufacturing applications, and digital engineering practice. Evaluate and introduce relevant new methods to the team.

Qualifications

Required

• MS or PhD in Mechanical, Aerospace, Civil, or Structural Engineering, or a closely related engineering discipline. A computer science background is considered only with demonstrated hands-on engineering application experience.
• 5+ years of experience at the intersection of engineering practice and software or digital tool development, with direct exposure to simulation, structural analysis, or design workflows.
• Hands-on experience with FEA, CFD, or CAD toolchains (ANSYS, ABAQUS, SolidWorks, or similar) and the ability to automate, extend, or integrate those environments through scripting or APIs.
• Strong proficiency in Python and MATLAB for engineering automation, data processing, and tool development. Experience with both is expected given the team's existing toolchain.
• Demonstrated experience building and deploying AI/ML models for engineering or industrial applications, with validation against physical data.
• Proven ability to identify where digital tools can have genuine engineering impact, and to build those tools from concept through production use.
• Working knowledge of composite blade or wind turbine structural behavior sufficient to evaluate whether tool outputs are physically plausible.

Strongly Valued

• Direct experience in wind energy, aerospace, or a closely related structural composites industry, working inside engineering teams rather than as an external software or AI provider.
• Experience with parametric and computational design workflows, including geometry generation, design space exploration, and simulation-based optimization.
• Familiarity with modern machine learning frameworks and experience applying them to physics-informed or engineering datasets.
• Experience with agentic AI and LLM orchestration frameworks applied to engineering workflow automation, with the judgment to evaluate and adopt new tooling as the landscape evolves.
• Background in structural health monitoring, signal processing, or NDT data processing for structural applications.
• Strong knowledge of data protection and information security practices, with the ability to build AI tools and data pipelines that safeguard company proprietary engineering data and comply with enterprise security standards.
• Experience with CI/CD workflows, version control (Git), and software development practices in an engineering environment.
• Familiarity with inspection data formats common in the wind industry: drone/visual inspection imagery, ultrasonic NDT, thermography.

What We're Looking For

The ideal candidate has felt the friction of real engineering workflows from the inside. You have run simulations, wrestled with data pipelines, or dealt with manual analysis processes that should be automated, and you built something to fix it. You are energized by the gap between what digital tools can do and what engineers actually use, and you know that closing that gap requires both technical capability and engineering credibility.

You hold AI-generated outputs to the same standard as any other engineering calculation: it needs to be physically plausible, validated against evidence, and defensible to an experienced engineer. You are as comfortable in a conversation about composite structural mechanics as you are writing a Python automation script.

Strong interpersonal, collaboration, and communication skills are essential. Envision's culture is entrepreneurial and fast-moving. Desire and ability to work effectively across cultural boundaries and international time zones is critical.

Work Arrangement & Travel

• Work arrangement: Hybrid
• Travel: Up to 15% international travel, including field deployments and collaboration with global teams.

Envision Energy is an Equal Opportunity Employer. Employment decisions are made without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, veteran status, or other characteristics protected by law.