AI Software Test Engineer

Spectraforce Technologies; Ann Arbor (MI); Hybrid; USD 90,000 - 130,000; Full time

Job summary

Spectraforce Technologies in Ann Arbor, MI is seeking a Mid-Level AI Software Test Engineer to design, automate, and execute testing strategies for AI-powered applications, machine learning systems, AI agents, copilots, and generative AI solutions.

This role combines traditional software quality engineering with emerging AI validation techniques to ensure AI systems are reliable, safe, accurate, performant, and production‑ready.

Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Information Systems, or related field.
• 3–6 years of software testing, QA automation, or quality engineering experience.
• Experience developing automated test solutions using Python, Java, JavaScript/TypeScript, or C#.
• Experience with API testing and automation tools.
• Strong understanding of SDLC, Agile methodologies, and CI/CD pipelines.
• Experience testing distributed systems, web applications, and APIs.

Responsibilities

• Develop comprehensive testing strategies for AI applications, platforms, and services.
• Validate AI model outputs for accuracy, consistency, 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 AI guardrails, business rules, permissions, and governance controls.
• Perform adversarial, negative, and edge‑case testing to identify model failures and hallucinations.
• Build and maintain automated test frameworks for AI applications.
• Develop automated evaluation pipelines for AI responses and workflows.
• Integrate AI testing into CI/CD pipelines.
• Implement automated quality scoring and regression detection.
• Create reusable test data, mocks, simulators, and validation frameworks.
• Test AI agents, workflows, APIs, MCP integrations, and tool‑calling capabilities.
• Validate integrations with external systems, data sources, and enterprise services.
• Verify performance, reliability, scalability, and resiliency of AI workloads.
• Execute load and stress testing for AI services.
• Partner with software engineers, AI engineers, product owners, architects, and security teams.
• Participate in design reviews and provide quality feedback during development.
• Contribute to test strategy, quality standards, and best practices.
• Support production readiness reviews and defect triage activities.

Skills

Prompt Testing

Response Evaluation

Hallucination Detection

Agent Workflow Validation

RAG Validation

AI Safety Testing

AI Regression Testing

AI Benchmarking

Test Automation

API Testing

Integration Testing

Performance Testing

Load Testing

Security Testing

Defect Analysis

Root Cause Investigation

Education

Bachelor's degree in Computer Science, Software Engineering, Information Systems, or related field

Tools

Selenium

Playwright

Postman

JUnit / PyTest

GitHub Actions

Jenkins

Docker

Kubernetes

Azure

AWS

GCP

Job description

Title

AI Software Test Engineer (Mid-Level)

Location

Ann Arbor, MI

Duration

18 months (6 months 100% onsite; subsequent 6 months with 4 days onsite and 1 remote day chosen by candidate)

Position Summary

We are seeking a Mid‑Level AI Software Test Engineer to design, automate, and execute testing strategies for AI‑powered applications, machine learning systems, AI agents, copilots, and generative AI solutions. This role combines traditional software quality engineering with emerging AI validation techniques to ensure AI systems are reliable, safe, accurate, performant, and production‑ready.

The ideal candidate has a strong software testing background, experience building automated test frameworks, and an interest in AI technologies such as LLMs, agents, RAG systems, MCP integrations, and machine learning models. AI engineering organizations increasingly emphasize AI evaluation frameworks, automation, reliability, governance, and production quality, making testing a critical function in AI delivery.

Key Responsibilities

AI Quality Engineering

• Develop comprehensive testing strategies for AI applications, platforms, and services.
• Validate AI model outputs for accuracy, consistency, 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 AI guardrails, business rules, permissions, and governance controls.
• Perform adversarial, negative, and edge‑case testing to identify model failures and hallucinations.

Automation

• Build and maintain automated test frameworks for AI applications.
• Develop automated evaluation pipelines for AI responses and workflows.
• Integrate AI testing into CI/CD pipelines.
• Implement automated quality scoring and regression detection.
• Create reusable test data, mocks, simulators, and validation frameworks.

Platform & Integration Testing

• Test AI agents, workflows, APIs, MCP integrations, and tool‑calling capabilities.
• Validate integrations with external systems, data sources, and enterprise services.
• Verify performance, reliability, scalability, and resiliency of AI workloads.
• Execute load and stress testing for AI services.

Collaboration

• Partner with software engineers, AI engineers, product owners, architects, and security teams.
• Participate in design reviews and provide quality feedback during development.
• Contribute to test strategy, quality standards, and best practices.
• Support production readiness reviews and defect triage activities.

Required Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Information Systems, or related field.
• 3‑6 years of software testing, QA automation, or quality engineering experience.
• Experience developing automated test solutions using Python, Java, JavaScript/TypeScript, or C#.
• Experience with API testing and automation tools.
• Strong understanding of test automation, software development lifecycle (SDLC), Agile methodologies, and CI/CD pipelines.
• Experience testing distributed systems, web applications, and APIs.

Preferred Qualifications

• Experience testing generative AI applications, LLM‑based systems, AI agents, RAG applications, and MCP‑based integrations.
• Familiarity with OpenAI, Claude, Gemini, and Azure OpenAI.
• Experience building evaluation and benchmarking frameworks for AI solutions.
• Experience testing cloud‑native applications on Azure, AWS, or GCP.
• Knowledge of responsible AI, AI governance, and AI risk management practices, with alignment to enterprise governance, risk, privacy, and compliance requirements.

Technical Skills

AI Testing

• Prompt Testing
• Response Evaluation
• Hallucination Detection
• Agent Workflow Validation
• RAG Validation
• AI Safety Testing
• AI Regression Testing
• AI Benchmarking

Quality Engineering

• Test Automation
• API Testing
• Integration Testing
• Performance Testing
• Load Testing
• Security Testing
• Defect Analysis
• Root Cause Investigation

Tools & Technologies

• Selenium
• Playwright
• Postman
• JUnit / PyTest
• GitHub Actions
• Jenkins
• Docker
• Kubernetes
• Cloud Platforms: Azure, AWS, GCP

Success Measures

• Establish reliable automated AI testing coverage.
• Detect AI quality issues before production deployment.
• Reduce regression defects across AI releases.
• Improve confidence in AI model and agent behavior.
• Enable safe, scalable delivery of AI‑powered features.
• Ensure AI solutions meet quality, security, and governance requirements.

Example Projects

• Testing AI chat assistants and copilots
• Validating MCP tools and AI agent workflows
• Evaluating RAG search quality and grounding accuracy
• Automating AI response evaluation frameworks
• Testing AI‑powered trading assistants and workflow automation
• Performance testing AI services and orchestration platforms

Typical Level

3‑6 years of software quality engineering experience, with 1‑3 years exposure to AI/ML or generative AI technologies.

Equivalent Titles

• AI Software Test Engineer
• AI Quality Engineer
• Generative AI Test Engineer
• AI Automation Engineer
• AI Validation Engineer
• Software Engineer in Test (AI) (SDET‑AI)

This role is suitable for an engineer who can independently own AI testing and automation efforts while partnering closely with AI developers, architects, and product teams to ensure production‑quality AI solutions.