Software Developer Engineer Test

Aquent; Ann Arbor (MI); Vor Ort; USD 90.000 - 120.000; Vollzeit

Zusammenfassung

Aquent partners with a cutting-edge organization to shape the future of AI quality. The Mid-Level AI Software Test Engineer will design, automate, and execute testing strategies for AI-powered applications, ML systems, and autonomous agents.

You will validate model outputs, guardrails, and governance to ensure responsible deployment and high-quality experiences. Join a team focused on scalable AI features, rigorous testing, and production-ready solutions, collaborating with software and AI

Qualifikationen

• Bachelor's degree in Computer Science, Software Engineering, Information Systems, or a related technical field.
• 3-6 years of progressive experience in software testing, QA automation, or quality engineering.
• Experience developing automated test solutions using Python, Java, JavaScript/TypeScript, or C#.
• Demonstrated API testing experience with tools like Postman.
• Strong understanding of test automation principles and SDLC/Agile.
• Experience integrating testing into CI/CD pipelines (GitHub Actions, Jenkins).
• Experience testing distributed systems, web apps, and APIs.
• Familiarity with Docker and Kubernetes.
• Experience with cloud platforms (Azure, AWS, or GCP).
• Proficiency in quality engineering concepts including Defect Analysis and Root Cause Investigation.

Aufgaben

• Develop and implement comprehensive testing strategies for AI applications and services.
• Validate AI model outputs for accuracy, reliability, and safety.
• Design and execute functional, integration, end-to-end, regression, and performance tests for AI solutions.
• Create test cases for prompt-driven, agentic, and retrieval-based AI workflows.
• Validate guardrails, permissions, and governance controls for responsible AI deployment.
• Perform adversarial, negative, and edge-case testing to identify failures and hallucinations.
• Build automated test frameworks for AI applications and CI/CD integration.
• Develop automated evaluation pipelines for AI responses and workflows.
• Create reusable test data, mocks, simulators, and validation frameworks.

Kenntnisse

Python

Java

JavaScript/TypeScript

C#

API testing

CI/CD

Git

Ausbildung

Bachelor's degree in CS/SE

Tools

Postman

Docker

Kubernetes

Azure

AWS

GCP

Selenium

Playwright

JUnit

PyTest

Jobbeschreibung

Aquent, a global leader in talent solutions, is partnering with an innovative and influential organization that is at the forefront of leveraging artificial intelligence to transform its industry. This company is dedicated to building robust, reliable, and cutting-edge AI-powered applications that drive significant impact for its users and stakeholders. Join a team where your expertise will directly contribute to shaping the future of AI technology and ensuring its responsible and high-quality deployment.

Shape the Future of AI Quality as a Mid-Level AI Software Test Engineer!

Are you passionate about the intersection of software quality and groundbreaking artificial intelligence? We are seeking a dynamic and experienced engineer to play a critical role in ensuring the integrity, safety, and performance of our next-generation AI solutions. In this pivotal role, you will be instrumental in designing, automating, and executing advanced testing strategies for AI-powered applications, machine learning systems, intelligent agents, copilots, and generative AI solutions. You will combine your strong software quality engineering background with emerging AI validation techniques to ensure our AI systems are not only innovative but also reliable, accurate, performant, and production-ready. Your work will directly enhance user trust and enable the scalable delivery of AI-powered features, making a significant impact on our product quality and strategic initiatives.

What You Will Do:

• Develop and implement comprehensive testing strategies for a diverse portfolio of AI applications, platforms, and services.
• Validate AI model outputs for critical attributes such as accuracy, consistency, reliability, and safety, ensuring high-quality user experiences.
• Design and execute a full spectrum of tests including functional, integration, end-to-end, regression, and performance testing for AI solutions.
• Create sophisticated test cases tailored for prompt-driven, agentic, and retrieval-based AI workflows.
• Validate AI guardrails, business rules, permissions, and governance controls to ensure responsible AI deployment.
• Perform adversarial, negative, and edge-case testing to proactively identify potential model failures and hallucinations.
• Build and maintain robust automated test frameworks specifically designed for AI applications, streamlining the testing process.
• Develop automated evaluation pipelines for AI responses and workflows, facilitating continuous quality assessment.
• Integrate AI testing seamlessly into CI/CD pipelines, promoting a culture of continuous quality and rapid iteration.
• Implement automated quality scoring and regression detection mechanisms to maintain high standards across releases.
• Create reusable test data, mocks, simulators, and validation frameworks to enhance testing efficiency and coverage.
• Test AI agents, workflows, APIs, and tool-calling capabilities, ensuring smooth and effective operations.
• Validate integrations with external systems, diverse data sources, and enterprise services.
• Verify the performance, reliability, scalability, and resiliency of AI workloads through rigorous testing.
• Execute load and stress testing to ensure AI services can handle anticipated demands.
• Collaborate closely with software engineers, AI engineers, product owners, architects, and security teams throughout the development lifecycle.
• Actively participate in design reviews, providing crucial quality feedback from the early stages of development.
• Contribute to defining test strategy, establishing quality standards, and promoting best practices across the organization.
• Support production readiness reviews and lead defect triage activities to ensure timely resolution of issues.

Required Qualifications:

• Bachelor's degree in Computer Science, Software Engineering, Information Systems, or a related technical field.
• 3-6 years of progressive experience in software testing, QA automation, or quality engineering.
• Proven experience developing automated test solutions using one or more of the following languages: Python, Java, JavaScript/TypeScript, C#.
• Demonstrated experience with API testing and automation tools (e.g., Postman).
• Strong foundational understanding of test automation principles and best practices.
• Solid grasp of the Software Development Lifecycle (SDLC) and Agile methodologies.
• Experience integrating testing into CI/CD pipelines (e.g., GitHub Actions, Jenkins).
• Experience testing distributed systems, web applications, and APIs.
• Familiarity with containerization technologies like Docker and orchestration platforms such as Kubernetes.
• Experience with testing on cloud platforms (Azure, AWS, or GCP).
• Proficiency in quality engineering concepts including Defect Analysis and Root Cause Investigation.

Preferred Qualifications (Nice-to-Have):

• Experience testing generative AI applications, LLM-based systems, AI agents, or RAG applications.
• Familiarity with leading AI models and platforms such as OpenAI, Claude, Gemini, or Azure OpenAI.
• Experience building evaluation and benchmarking frameworks specifically for AI solutions.
• Knowledge of responsible AI principles, AI governance frameworks, and AI risk management practices.
• Experience with AI-specific testing techniques including Prompt Testing, Response Evaluation, Hallucination Detection, Agent Workflow Validation, RAG Validation, AI Safety Testing, AI Regression Testing, and AI Benchmarking.
• Familiarity with test automation frameworks like Selenium, Playwright, JUnit, or PyTest.
• Exposure to various quality engineering domains such as Performance Testing, Load Testing, and Security Testing.