SDET Contractor (Agentic AI)

Location: Waterloo, Ontario, Canada; hybrid working policy applies

Salary: $51.61–$77.42 CAD per hour

Company

hirify.global is the consumer entertainment and technology brand of Sony Interactive Entertainment, delivering gaming hardware, network services, and interactive entertainment experiences.

What you will do

• Develop QE strategies and test plans for Agentic AI systems, backend services, APIs, microservices, and integrations.
• Design and maintain automated frameworks for functional, integration, contract, regression, and end-to-end testing.
• Test multi-step AI workflows, tool selection and invocation, task completion, failure handling, guardrails, and prompt-based attacks.
• Evaluate AI-generated responses for accuracy, relevance, groundedness, consistency, and expected behavior.
• Integrate automated tests into CI/CD pipelines, define quality gates, and establish quality metrics.
• Investigate distributed-system failures, perform root-cause analysis, support defect triage, and assess release readiness.

Requirements

• Bachelor’s degree in Computer Science, Engineering, Information Technology, or a related field, or equivalent practical experience.
• 4+ years of experience in SDET, Quality Engineering, Software Engineering, or a related discipline.
• Strong experience testing REST APIs, backend services, microservices, distributed systems, JSON, schemas, authentication, and error handling.
• Hands-on experience developing automated tests with Python, Java, JavaScript, TypeScript, or a similar language.
• Experience with functional, integration, regression, contract, and end-to-end testing, as well as CI/CD workflows and Git.
• Hands-on experience testing Generative AI, LLM-powered, or Agentic AI systems and evaluating non-deterministic behavior beyond exact-match assertions.

Nice to have

• Experience with Agentic AI planning, memory, state management, evaluation datasets, semantic evaluation, LLM-as-a-Judge, groundedness, relevance, or hallucination detection.
• Experience with LangSmith, DeepEval, Ragas, Arize Phoenix, Promptfoo, Pact, OpenAPI, or Swagger.
• Experience with RAG systems, event-driven architectures, Kafka, Docker, Kubernetes, AWS, or performance and resiliency testing.

Culture & Benefits

• Hybrid working environment in Waterloo, Ontario.
• Inclusive workplace with equal-opportunity and fair-chance employment practices.
• Background checks are conducted at the offer stage.

Hiring process

• Background checks may include criminal record checks for some roles and are conducted at the offer stage.