AI QA Evaluation Engineer

APTIV INDIA; Dublin; On-site; EUR 70,000 - 110,000; Full time

Benefits offered by this job

Personal holidays

Healthcare

Pension

Tax saver scheme

Free onsite breakfast & lunch

Discounted corporate gym membership

Multicultural environment

Learning and development

Internal & external training

Job summary

Aptiv is seeking an AI QA / Evaluation Engineer (Enterprise AI Agents) in Dublin to define and advance testing and evaluation practices for AI agents and agentic workflows. You will collaborate with stakeholders and engineering teams to ensure reliability, compliance, and fit-for-purpose solutions before release.

Reporting to the AI Platform Manager, you will own evaluation frameworks, test standards, and environment maintenance, supporting user acceptance testing and validation of end-user

Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Information Systems or a related field.
• Experience in software testing, QA engineering or validation roles within enterprise technology environments.
• Strong understanding of test design, test execution and defect management practices.
• Experience working with development teams in agile or Kanban-based delivery environments.
• Ability to define structured test approaches for complex systems, including integration and end-to-end scenarios.
• Experience working across engineering, architecture and control functions in a governed enterprise environment.
• Strong analytical and problem-solving skills with attention to detail.
• Understanding of AI/ML or automation solutions and their unique testing considerations is highly desirable.

Responsibilities

• Define and implement testing and evaluation frameworks for AI agents and agentic workflows, covering functional quality, groundedness, safety, reliability, and performance.
• Develop and execute test plans, test cases, evaluation criteria, test data, datasets, and benchmark scenarios to ensure consistent and repeatable validation.
• Partner with DevOps Agent Engineers and Release / Operations Engineers to validate AI solutions throughout build, integration, pre-production, and deployment phases.
• Work with AI Architects to ensure evaluation approaches align with solution design, risk profiles, enterprise standards, and responsible AI requirements.
• Own and maintain development and test environments for AI agents, ensuring stability, availability, and alignment with enterprise platform standards.
• Support business users during user acceptance testing and validate end-user developed agents prior to publishing, ensuring solutions are fit for purpose and meet enterprise quality and governance requirements.
• Identify, log, and track defects, working closely with engineering teams to support resolution, retesting, and continuous improvement of testing practices, tooling, and automation.
• Collaborate with Cyber Security, Legal, and Data Privacy teams to ensure testing addresses compliance, security, and responsible AI requirements, while maintaining clear documentation of test results, quality metrics, and evaluation outcomes.

Skills

Software testing

QA engineering

Test design

Agile / Kanban

Structured test approaches

Governed enterprise environments

Analytical thinking

AI/ML testing considerations

Education

Bachelor's degree in Computer Science / Software Engineering / Information Systems

Tools

Test automation tools

Scripting

CI/CD integrated testing

Job description

AI QA / Evaluation Engineer (Enterprise AI Agents)

The QA / Evaluation Engineer will work directly with business stakeholders and engineering teams to define, execute and continuously improve testing and evaluation practices for enterprise AI agents and agentic workflows.

Reporting to the AI Platform Manager, this role is responsible for ensuring all AI solutions are functional, reliable, compliant and fit for purpose prior to release. The role owns evaluation frameworks and test standards, and is accountable for maintaining development and test environments to support consistent, high-quality delivery.

The role will also liaise directly with business users to support user acceptance testing and to validate end-user built agents ahead of publishing, ensuring alignment with enterprise standards, governance requirements and quality thresholds.

Responsibilities

• Define and implement testing and evaluation frameworks for AI agents and agentic workflows, covering functional quality, groundedness, safety, reliability, and performance.
• Develop and execute test plans, test cases, evaluation criteria, test data, datasets, and benchmark scenarios to ensure consistent and repeatable validation.
• Partner with DevOps Agent Engineers and Release / Operations Engineers to validate AI solutions throughout build, integration, pre-production, and deployment phases.
• Work with AI Architects to ensure evaluation approaches align with solution design, risk profiles, enterprise standards, and responsible AI requirements.
• Own and maintain development and test environments for AI agents, ensuring stability, availability, and alignment with enterprise platform standards.
• Support business users during user acceptance testing and validate end-user developed agents prior to publishing, ensuring solutions are fit for purpose and meet enterprise quality and governance requirements.
• Identify, log, and track defects, working closely with engineering teams to support resolution, retesting, and continuous improvement of testing practices, tooling, and automation.
• Collaborate with Cyber Security, Legal, and Data Privacy teams to ensure testing addresses compliance, security, and responsible AI requirements, while maintaining clear documentation of test results, quality metrics, and evaluation outcomes.

Required Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Information Systems or a related field.
• Experience in software testing, QA engineering or validation roles within enterprise technology environments.
• Strong understanding of test design, test execution and defect management practices.
• Experience working with development teams in agile or Kanban-based delivery environments.
• Ability to define structured test approaches for complex systems, including integration and end-to-end scenarios.
• Experience working across engineering, architecture and control functions in a governed enterprise environment.
• Strong analytical and problem-solving skills with attention to detail.
• Understanding of AI/ML or automation solutions and their unique testing considerations is highly desirable.

Preferred Qualifications

• Experience with AI evaluation frameworks, including groundedness, safety, hallucination detection and performance testing.
• Familiarity with Microsoft Copilot Studio, Azure AI Foundry or similar enterprise AI platforms.
• Experience with test automation tools, scripting or CI/CD-integrated testing approaches.
• Exposure to data validation, prompt testing or evaluation dataset design.
• Experience working with enterprise governance, responsible AI, security and compliance requirements.
• Experience operating in global, matrixed or regulated enterprise environments.

Why join Aptiv

You grow at Aptiv.

Aptiv's winning culture is global by design. We bring together diverse perspectives, cultures, and business contexts to solve our customers' toughest challenges. In this environment, every individual can grow, lead, and make an impact, regardless of background, because inclusion fuels how we innovate and win.

You make an impact at Aptiv.

One of the strengths of humanity is our drive to progress, to improve, to achieve more tomorrow than we did yesterday. People need solutions they can trust when it matters most. At Aptiv, you are building those solutions every day.

You have support at Aptiv.

We ensure you have the resources and support you need to take care of your family, your physical health, and your mental health with a competitive benefits package.

Your Benefits at Aptiv

• Benefits/Perks: Personal holidays, Healthcare, Pension, Tax saver scheme, Free Onsite Breakfast & Lunch, Discounted Corporate Gym Membership.
• Multicultural environment.
• Learning, professional growth and development in a world-recognized international environment.
• Access to internal & external training, coaching & certifications.
• Recognition for innovation and excellence.
• Access to transportation: Grand Canal Dock is well-connected to public transportation, inc