Mid-Level AI Software Test Engineer

Indotronix International Corporation•Ann Arbor, MI

About The Position

We are seeking a Mid-Level AI Software Test Engineer to lead the quality assurance, validation, and automation efforts for AI-powered applications, machine learning systems, AI agents, copilots, and generative AI solutions. This role combines traditional software quality engineering practices with emerging AI testing methodologies to ensure AI systems are accurate, reliable, secure, scalable, and production-ready. The ideal candidate has a strong foundation in software testing and automation, along with experience or exposure to AI technologies such as Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents, Model Context Protocol (MCP) integrations, and machine learning platforms. This role plays a critical part in establishing AI quality standards, evaluation frameworks, governance controls, and automated testing capabilities across the AI development lifecycle.

Requirements

Bachelor's degree in Computer Science, Software Engineering, Information Systems, or a related technical field.
3–6 years of experience in software testing, quality assurance, quality engineering, or test automation.
Experience developing automated testing solutions using one or more of the following: Python, Java, JavaScript / TypeScript, C#
Experience with API testing and automation frameworks.
Strong understanding of: Test automation methodologies, Software Development Lifecycle (SDLC), Agile development practices, CI/CD pipelines and DevOps principles
Experience testing distributed systems, web applications, APIs, and enterprise platforms.
Strong analytical, troubleshooting, and problem-solving skills.
Excellent verbal and written communication skills.

Nice To Haves

Experience testing Generative AI applications
Experience testing LLM-based systems
Experience testing AI agents and autonomous workflows
Experience testing Retrieval-Augmented Generation (RAG) solutions
Experience testing MCP-based integrations
Familiarity with leading AI platforms and models, including: OpenAI, Azure OpenAI, Anthropic Claude, Google Gemini
Experience developing AI evaluation, benchmarking, and validation frameworks.
Experience testing cloud-native applications on: Microsoft Azure, Amazon Web Services (AWS), Google Cloud Platform (GCP)
Knowledge of: Responsible AI principles, AI governance frameworks, AI risk management and compliance practices, Privacy and security considerations for AI systems

Responsibilities

Develop and execute comprehensive testing strategies for AI applications, platforms, and services.
Validate AI-generated outputs for accuracy, consistency, relevance, reliability, and safety.
Design and perform functional, integration, end-to-end, regression, and performance testing for AI-powered solutions.
Create and maintain test cases for prompt-driven applications, AI agents, RAG systems, and workflow orchestration platforms.
Validate AI guardrails, business rules, permissions models, compliance requirements, and governance controls.
Conduct adversarial, negative, and edge-case testing to identify hallucinations, unsafe behavior, model drift, and failure scenarios.
Establish quality benchmarks and acceptance criteria for AI solutions.
Design, build, and maintain automated test frameworks for AI applications and services.
Develop automated evaluation pipelines to assess AI responses, workflows, and model behavior.
Integrate AI testing processes into CI/CD pipelines.
Implement automated quality scoring, benchmarking, and regression detection capabilities.
Create reusable test datasets, simulators, mocks, and validation frameworks to support scalable testing.
Test AI agents, copilots, APIs, workflow engines, MCP integrations, and tool-calling capabilities.
Validate integrations with enterprise systems, external APIs, databases, and knowledge repositories.
Verify performance, reliability, scalability, resiliency, and availability of AI workloads.
Execute load, stress, and performance testing for AI applications and services.
Identify, document, and troubleshoot defects across application, infrastructure, model, and integration layers.
Partner closely with software engineers, AI engineers, solution architects, product owners, and security teams.
Participate in solution design reviews and provide quality-related recommendations early in the development lifecycle.
Contribute to testing standards, methodologies, best practices, and AI quality frameworks.
Support production readiness reviews, defect triage, root cause analysis, and continuous improvement initiatives.
Promote responsible AI practices and help ensure alignment with organizational governance, privacy, risk, and compliance requirements.