Senior SDET for AI Agents QA | Industrial Systems

Nexxa.ai; Canada; On-site; CAD 120,000 - 160,000; Full time

Job summary

Nexxa.ai in Canada is seeking a Senior / Staff SDET to own quality for Nexxa’s AI agent systems. You’ll design test frameworks, write production-grade code for evaluation harnesses, simulators, and CI/CD gates, and perform hands-on testing of agent behavior in industrial settings.

Collaborate with ML and backend teams to define what good looks like, build automated checks, run red-team sessions, and document clear bug reports.

Qualifications

• 5+ years as an SDET, QA engineer, or software engineer with testing focus.
• Proven manual and automated testing experience, including exploratory testing.
• Strong Python skills and software engineering mindset for frameworks and tooling.

Responsibilities

• Design, build, and maintain test frameworks, evaluation harnesses, and regression suites for LLM-based agents.
• Create automated pipelines to run evals and tests on every model, prompt, or tool change and enforce quality gates in CI/CD.
• Develop simulators and sandbox environments for industrial systems and tool APIs for safe, scalable testing.
• Implement API, contract, integration, and end-to-end tests for services and orchestration layers.
• Perform manual and exploratory testing of agent behavior, review traces, and validate releases.
• Lead red-team exercises and translate findings into automated test cases.

Skills

Python programming

Test automation

CI/CD

LLM testing

Docker

Kubernetes

API testing

Manual testing

Telemetry & observability

Strong communication

Tools

GitHub Actions

GitLab CI

Jenkins

LangSmith/ eval tooling

Job description

Nexxa.ai in Canada is seeking a Senior / Staff SDET to own quality for Nexxa’s AI agent systems. You’ll design test frameworks, write production-grade code for evaluation harnesses, simulators, and CI/CD gates, and perform hands-on testing of agent behavior in industrial settings.

Collaborate with ML and backend teams to define what good looks like, build automated checks, run red-team sessions, and document clear bug reports.