Quality Engineer (QE) / SDET – AI Chatbot Validation

Apptoza Inc.; Toronto; On-site; CAD 90,000 - 130,000; Full time

Job summary

Apptoza Inc. in Toronto seeks a seasoned AI-first Senior Quality Engineer who will empower the DevOps enablement team to deliver top quality and uphold quality values and principles.

The role collaborates across DevOps, Development, Product, and QE to design and execute AI-focused tests and build scalable automation The candidate will define test strategies, create data, integrate QA into CI/CD pipelines, and assess AI integrations, APIs, microservices, and data pipelines with a focus on

Qualifications

• 5+ years of relevant experience in Quality Engineering, QA, automation, or software development.
• 5+ years of programming experience with Java, Python, Groovy, or comparable language.
• 5+ years of experience building and maintaining test automation frameworks.
• Experience testing AI-powered applications, chatbots, LLM validations, APIs, or generative AI features.
• Hands-on experience with Selenium, Cucumber/Gherkin, Playwright, RestAssured, or similar automation technologies.

Responsibilities

• Partner with DevOps, Development, Product, and QE teams to design and execute AI-focused tests.
• Define quality strategies, test plans, and test data for functional, API, and regression testing.
• Design, develop, and maintain scalable test automation frameworks using Java, Python, or Groovy.
• Build automated tests for AI-enabled features including chatbot validation and latency considerations.
• Integrate automated testing and AI quality checks into CI/CD pipelines.

Skills

Quality Engineering

Java

Python

Groovy

Automation Frameworks

AI Testing

Education

Bachelor's degree in CS/CE

Tools

Selenium

Cucumber/Gherkin

Playwright

RestAssured

JUnit

TestNG

ReadyAPI

JMeter

Job description

Quality Engineer (QE) / SDET - AI Chatbot Validation

Job Description:

We are looking for a seasoned AI first Senior Quality Engineer who is empowered to help the DevOps enablement team deliver highest level quality and is responsible for ensuring the team live quality values and principles. The DevOps team is responsible for providing pipelines, metrics and tools for use by application development teams. The incumbent will actively participate in gathering quality criteria from the user community, developing a backlog of items, prioritizing them with the teams and delivering them continually.

What You Will Do:

• Partner with DevOps, Development, Product, and QE teams to design and execute exploratory, automated, and AI-focused tests that ensure product quality.
• Define quality strategies, test plans, test cases, and test data for functional, integration, system, regression, API, database, and acceptance testing.
• Design, develop, and maintain scalable test automation frameworks using Java, Python, or Groovy.
• Build automated tests for AI-enabled features, including, AI chatbot response validation, prompt behavior, response accuracy, hallucination risks, safety, reliability, latency, and regression coverage.
• Validate AI integrations, APIs, microservices, data pipelines, model interactions, and third-party services.
• Establish testing approaches for both deterministic and non-deterministic AI behavior, including evaluation datasets, expected behavior, quality thresholds, and repeatability.
• Integrate automated testing and AI quality checks into CI/CD pipelines in partnership with DevOps teams.
• Use tools and frameworks such as Selenium, Cucumber/Gherkin, Playwright, RestAssured, JUnit, TestNG, ReadyAPI, and JMeter.
• Identify, document, prioritize, and track defects through resolution.
• Analyze test coverage, quality trends, AI evaluation results, and production feedback to identify gaps and drive continuous improvement.
• Collaborate with cross-functional Agile teams to deliver reliable, secure, and user-focused product features.
• Communicate test results, risks, quality metrics, and release recommendations clearly to technical and non-technical stakeholders.

What You Will Need to Succeed:

• 5+ years of relevant experience in Quality Engineering, Quality Assurance, test automation, or software development.
• 5+ years of programming experience with Java, Python, Groovy, or a comparable language.
• 5+ years of experience building and maintaining test automation frameworks.
• Experience testing AI or machine learning-powered applications, Chatbots, LLM validations, APIs, conversational systems, or generative AI features.
• Hands‑on experience with Selenium, Cucumber/Gherkin, Playwright, RestAssured, or similar automation technologies.
• Experience testing functional and non‑functional requirements, APIs, integrations, databases, microservices, and regression suites.
• Experience with testing frameworks and tools such as JUnit, TestNG, qTest, ReadyAPI, and JMeter.
• Understanding of TDD, ATDD, BDD, continuous testing, and risk‑based testing practices.
• Understanding of AI quality concepts such as prompt evaluation, grounding, accuracy, relevance, toxicity, bias, hallucination detection, and response consistency.
• Ability to create effective test data and evaluation datasets for AI‑driven functionality.
• Strong analytical, problem‑solving, communication, and technical documentation skills.
• Ability to work effectively in a fast‑paced, cross‑functional Agile environment.

Nice to Have:

• Experience with AI evaluation frameworks, LLM testing, prompt engineering, retrieval‑augmented generation, embeddings, or model observability.
• Experience with Git, Bitbucket, Jenkins, CI/CD pipelines, Artifactory, SonarQube, Jira, Confluence, AWS, Kubernetes, Maven, or Gradle.
• Experience testing cloud-native applications and distributed microservice architectures.
• Experience with security, performance, accessibility, or reliability testing.
• Experience developing automation scripts and reusable testing utilities.
• Experience with Tableau or other analytics and visualization platforms.
• CSTE certification or an equivalent quality engineering certification.
• Experience working directly with DevOps teams to implement automated quality gates and release controls.